3.1 3.

Review

Machine Learning-Based Modeling

for Structural Engineering: A
Comprehensive Survey and
Applications Overview

Bassey Etim, Alia Al-Ghosoun, Jamil Renno, Mohammed Seaid and M. Shadi Mohamed

https://doi.org/10.3390/buildings14113515
 buildings
Review
Machine Learning-Based Modeling for Structural Engineering:
A Comprehensive Survey and Applications Overview
Bassey Etim 1 , Alia Al-Ghosoun 2 , Jamil Renno 3, * , Mohammed Seaid 4 and M. Shadi Mohamed 1

1 School of Energy, Geoscience, Infrastructure and Society, Institute for Infrastructure & Environment,
Heriot-Watt University, Edinburgh EH14 4AS, UK; [email protected] (B.E.); [email protected] (M.S.M.)
2 Mechatronics Engineering Department, Philadelphia University, Amman 19392, Jordan;
[email protected]
3 Department of Mechanical & Industrial Engineering, College of Engineering, Qatar University,
Doha P.O. Box 2713, Qatar
4 Department of Engineering, University of Durham, South Road, Durham DH1 3LE, UK;
[email protected]
* Correspondence: [email protected]

Abstract: Modeling and simulation have been extensively used to solve a wide range of problems
in structural engineering. However, many simulations require significant computational resources,
resulting in exponentially increasing computational time as the spatial and temporal scales of the
models increase. This is particularly relevant as the demand for higher fidelity models and simu-
lations increases. Recently, the rapid developments in artificial intelligence technologies, coupled
with the wide availability of computational resources and data, have driven the extensive adoption
of machine learning techniques to improve the computational accuracy and precision of simulations,
which enhances their practicality and potential. In this paper, we present a comprehensive survey of
the methodologies and techniques used in this context to solve computationally demanding problems,
such as structural system identification, structural design, and prediction applications. Specialized
deep neural network algorithms, such as the enhanced probabilistic neural network, have been the
subject of numerous articles. However, other machine learning algorithms, including neural dynamic
classification and dynamic ensemble learning, have shown significant potential for major advance-
Citation: Etim, B.; Al-Ghosoun, A.; ments in specific applications of structural engineering. Our objective in this paper is to provide a
Renno, J.; Seaid, M.; Mohamed, M.S.
state-of-the-art review of machine learning-based modeling in structural engineering, along with its
Machine Learning-Based Modeling
applications in the following areas: (i) computational mechanics, (ii) structural health monitoring,
for Structural Engineering: A
(iii) structural design and manufacturing, (iv) stress analysis, (v) failure analysis, (vi) material mod-
Comprehensive Survey and
eling and design, and (vii) optimization problems. We aim to offer a comprehensive overview and
Applications Overview. Buildings
2024, 14, 3515. https://doi.org/
provide perspectives on these powerful techniques, which have the potential to become alternatives
10.3390/buildings14113515 to conventional modeling methods.

Academic Editor: Mijia Yang

Keywords: machine learning; computational mechanics; structural health monitoring; structural design
Received: 4 September 2024 and manufacturing; stress analysis; failure analysis; material modeling and design; optimization problems
Revised: 8 October 2024
Accepted: 16 October 2024
Published: 3 November 2024
1. Introduction
Machine learning (ML) is a key artificial intelligence technology that has started to
Copyright: © 2024 by the authors.
impact almost every scientific and engineering field in significant ways [1]. It holds the
Licensee MDPI, Basel, Switzerland. potential to become a game-changing technology within structural engineering disciplines,
This article is an open access article using tools such as image recognition [2], multi-object tracking [3], multi-target regres-
distributed under the terms and sion [4], thermal infrared stress identification [5], and engineering stress prediction [6]. The
conditions of the Creative Commons basic assumption regarding ML is that computers are able to detect and quantify complex
Attribution (CC BY) license (https:// patterns in data and identify embedded relations between different variables by means of
creativecommons.org/licenses/by/ generic algorithms [1,7]. The pattern detection and subsequent relation extraction from
4.0/). the data is achieved even if the underlying physical model is unknown [1]. Furthermore,

Buildings 2024, 14, 3515. https://doi.org/10.3390/buildings14113515 https://www.mdpi.com/journal/buildings

Buildings 2024, 14, 3515 2 of 36

using automated learning, ML algorithms can keep evolving with a continuous stream of
data, which enables continuous improvement [8]. Typically, an ML system comprises three
main components: (i) inputs, which include datasets containing images, signals, or features;
(ii) the ML algorithm; and (iii) the output [9]. In the context of ML, data and datasets
become the main ingredients [7]. In practice, a dataset consists of multiple data points that
each characterize an object of the study, while a data point describes a collection of features,
either measured or identified. Features are either categorical, ordinal, or numerical [10],
and each feature is stored in a vector and counted as a dimension in the feature space.
Thus, increasing the number of features increases the dimensionality of the space, which
could also improve the accuracy of the algorithm [11]. However, this also complicates the
problem and might require the application of dimension-reduction methods to make the
problem computationally feasible [1].
ML algorithms can be classified into the following three broad categories:
1. Supervised machine learning (SML), including various neural network models [12],
support vector machine [13], random forest [14], statistical regression [15], fuzzy
classifiers [16], and decision trees [17].
2. Unsupervised machine learning (UML), such as different clustering algorithms in-
cluding competitive learning [18], k-means and hierarchical clustering [19], and deep
Boltzmann machine [20].
3. Reinforcement machine learning (RML), which encompasses R-learning [21], Q-
learning [22], and temporal difference learning [23].
The decision to use a specific ML category depends on the perceived benefits for a
given scenario. SML is often chosen when labeled training data is available, allowing the al-
gorithm to learn from input–output pairs in order to make predictions and classifications on
new, unseen data [24]. SML is widely used in structural health monitoring applications and
material characterization. In contrast, UML is often used when large amounts of unlabeled
data are available for the training process. The objective in such cases would be to discover
hidden patterns in the data. UML is used for exploratory data analysis, anomaly detection,
and clustering data based on similar structures of features [25]. This leads to uncovering
insights and aids in dimension reduction. RML is the least commonly used category of ML
algorithms in structural engineering. RML uses an agent to learn how to make sequential
decisions in an environment to maximize a reward signal [26]. This category of ML can be
used in structural control applications by learning optimal control algorithms. The main
advantage of RML is its ability to optimize actions in dynamic environments and learn
complex strategies through interaction with the environment. These methods and their
various applications will be elaborated upon in the following subsection.
The remainder of the paper is organized as follows. In the following subsections, we
will briefly review the three categories of ML. Then, a section is dedicated to the applica-
tions of each category. Section 2 will present applications of SML; Section 3 will present
applications of UML, while applications of RML are surveyed in Section 4. Concluding
remarks are presented in Section 5.

1.1. Supervised Machine Learning

Currently, SML stands out as a prevalent sub-branch in the field. Typically, it operates
on the principle of learning by example. The term “supervised” stems from the concept
that these algorithms undergo training with oversight, akin to having a guiding instructor
overseeing the process [27]. During the training phase, input data is paired with predeter-
mined outputs [28]. The algorithm then scrutinizes the data to identify patterns linking
the inputs to the outputs. Post-training, the algorithm can process new, unseen inputs and
forecast the corresponding outputs based on the identified patterns [29]. Fundamentally,
an SML algorithm can be expressed succinctly as follows [30]:

y = f ( x ), (1)
Buildings 2024, 14, 3515 3 of 36

where y represents the predicted output, which is determined by a mapping function

assigning a class to an input value x. This function, linking input features to predicted
outputs, is generated by the ML model through its training process [31]. Most SML models
are trained and evaluated using the same basic process [32], as shown in Figure 1. Note
that in the workflow shown in Figure 1, data preparation is one of the most challenging
and time-consuming tasks. In this step, all necessary data is collected from various sources,
preprocessed, and split into training and test sets [33]. The actual model is built in the
next step using various types of SML algorithms. The model is then trained iteratively
by feeding it with the training set of data. In each iteration, the model aims to become
increasingly accurate by decreasing a predefined error criterion. Training is stopped when
a certain number of finite iterations is reached or when predefined stopping criteria are
met [34]. In the final step, the trained model is evaluated against the test data to determine
its performance and find ways to improve it. It should be noted that the whole process
is repeated multiple times until satisfactory results are observed in the model evaluation
stage [35].

Original Data Set

Training Set Test Set

Training Set Validation Set Test Set

Machine Learning
Algorithm

Predictive Model
Final Performance Estimation

Figure 1. Schematic of SML process.

SML comprises two primary types: classification and regression [36]. In the training
phase, a classification algorithm is presented with data points already assigned to specific
categories. Its task is to assign an input value to the appropriate category, aligning with the
provided training data [37]. An illustrative example of classification is shape identification,
where the algorithm is tasked with finding features to associate them with shape categories.
Hence, the algorithm creates a mapping function as shown in Figure 2. The second
most popular SML approach is the regression model. Regression algorithms are used for
continuous variables if there is a correlation between inputs and outputs [38]. Different
types of regression algorithms can be used in SML, including the regression tree, linear,
Bayesian linear, polynomial, and nonlinear regression [39]. The linear regression algorithm
produces a vector of coefficients that are then used to define the model [40], and the decision
tree produces a tree of if-then statements with specific values assigned to the tree branches.
The neural network, along with the optimization algorithm, comprises a trained model, i.e.,
weights and biases assigned to the nodes of a network so that the output is evaluated by
applying a number of numerical evaluations [41].
Buildings 2024, 14, 3515 4 of 36

Labelled Data
Prediction
Square

Triangle
Model Training

Labels

Test Data
Hexagon Square

Triangle

Figure 2. Schematic of SML classification process.

For both regression and classification, SML can be described by a matrix of input
features xi,j . Thus, the ith sample has the following vector of values [42]:

Xi = [ xi,1 , xi,2 , xi,3 , . . . , xi,d ], (2)

such that if Yi is the label associated with the ith sample, the training data are reformulated
in pairs, and the entire training data can be represented as [25]:

D = {( X1 , Y1 ), ( X2 , Y2 ), . . . , ( Xn , Yn )} ⊆ χd × τ, (3)
where χd is the dimensional feature space and τ is the label space. For the learning process,
a model called hypothesis h is assumed as:

h( Xi ) = Ŷi . (4)
In the next step, the squared loss error function Lsq is calculated as [25]:
n
1
Lsq =
n ∑ (h(Xi ) − Yi )2 . (5)
i =1

During the final step, the model undergoes iterative training to optimize h( x ) in order
to minimize the error Lsq . In the case of neural networks, backpropagation is employed
throughout the training process to compute and assess the gradients necessary for optimiza-
tion using algorithms such as gradient descent [43] or adaptive moment estimation (Adam)
optimizers. The Adam technique combines the principles of momentum optimization [44]
and root-mean-square propagation (RMSProp) [45], maintaining exponentially decaying
averages of past gradients and past squared gradients.

1.2. Unsupervised Machine Learning

UML commences with unlabeled data and aims to uncover unknown patterns that
facilitate a new, more condensed, or comprehensive representation of the contained infor-
mation [46]. Unlike SML, UML cannot be directly applied to regression or classification
problems since the input data lacks predefined outputs. Its objective is to unveil the in-
herent structure of the dataset, group the data based on similarities, and represent the
dataset in a compressed format, as depicted in Figure 3. Here, the input data are unlabeled,
meaning they lack categorization, and corresponding outputs are absent. Consequently,
the unlabeled input is used to train the machine learning model. Initially, the model scru-
tinizes the raw data to unveil any latent patterns, followed by the application of suitable
algorithms like k-means clustering [46] to forecast data behavior.
Buildings 2024, 14, 3515 5 of 36

Input Data Output

Square

Triangle

Hexagon

Unlabeled Data Interpretation Algorithm Processing

Figure 3. Schematic of UML classification process.

In general, UML models serve three primary tasks: association, clustering, and di-
mensionality reduction. Mathematically, this approach quantifies dissimilarity or distance
between two data points x and x ′ using a real number determined by a distance function
dist( x, x ′ ), which must satisfy certain conditions [47]:
′
i. dist( x, x ) ≥ 0,
′ ′
ii. dist( x, x ) = dist( x , x ),
′ ′
iii. dist( x, x ) = 0, i f x = x .
Subsequently, the data points are arranged into a specified number of clusters ci and the
centroid µ(ci ) of each cluster is then calculated by [48]:

1
µ ( ci ) = ∑ xj. (6)
| ci | x j ∈ ci

The Sum of Squared Error (SSE) can be used to evaluate the performance of the method
as [26]:
k
2
SSE = ∑ ∑ dist x j , µ(ci ) . (7)
i =1 x j ∈ c i

We note that the most accurate method is expected to have the smallest SSE error, which
can then be reduced by increasing the number of clusters k [49].

1.3. Reinforcement Machine Learning

In RML, the algorithm learns to achieve a goal in an uncertain and potentially complex
environment, typically using trial and error to come up with a solution to the problem
under study [50]. This method learns from an environment with a predefined set of
rules and is usually assumed to be deterministic [51]. An RML model interacts with the
environment through an agent that has a state in the environment. The agent interacts with
the environment through actions, which can change the state of the environment [52]. For
each action, the environment yields a new resulting state for the agent and a reward, as
shown in Figure 4. The goal of the model is to determine what actions lead to the maximum
reward [53]. To this end, RML works by estimating a value for each action. The value is
defined as the sum of the immediate reward received by taking an action and the expected
value of the new state multiplied by a scaling term [54]. In other words, the value of an
action is selected based on how good the next state will be after taking that action, along
with the expected future reward from that new state [55]. There are different methods to
calculate the value function, such as the Monte Carlo method, temporal difference learning,
and gradient descent methods [43].
Buildings 2024, 14, 3515 6 of 36

Input Data Output

Environment
Reward Best action

Selection of algorithm
State
Agent

Figure 4. Schematic of RML classification process.

1.3.1. Monte Carlo Method

The Monte Carlo method updates the value function as [56]:
 
V (Si ) + α Gi − V (Si−1 ) −→ V ( Si + 1 ) , (8)

where V is the value function, Si is the state at a given time i, α is the step size, and Gi is
the resulting reward.

1.3.2. Temporal Difference Learning

The temporal difference learning update of the value function is given by [56]:
 
V (Si ) + α Ri + γV (Si′−1 ) − V (Si−1 ) −→ V ( Si ) , (9)

where Ri is the immediate reward received after taking an action, Si′ is the state following
the action, and γ is a scaling term.

1.3.3. Gradient Descent Methods

Gradient descent methods are among the most popular approximators used in RML.
In other ML techniques, it is common to learn mappings between inputs and outputs
through complex differentiable functions. The same can be carried out to approximate the
value function in RML. The function can be updated as follows [43]:

(10)


W + α Q + V ∇V −→ W,

where V is the approximate value function and Q is the updated value estimate given the
immediate reward and future state of the action. Note that one needs to define W and
specify the variables in terms of i (of Equation (8)).

2. Supervised Machine Learning Applications

Supervised machine learning (SML) algorithms serve as potent predictive tools; how-
ever, owing to their complexity, they typically do not provide analytical relationships
between input and output data, often being termed as “black box” due to the potential
loss of insight into the underlying physics by users. The integration of such approaches
with the finite element method (FEM) has recently attracted considerable attention across
various research communities. A primary motivation driving this fusion is the aspiration
to enhance the balance between numerical precision and computational demand [57].

2.1. Data Requirement and Preprocessing

The primary determinant of the efficacy of SML lies in the dataset utilized for training
the SML model [58]. The performance of SML models directly correlates with the quality
Buildings 2024, 14, 3515 7 of 36

and relevance of the training data employed [59]. In the SML framework, the data can be
either synthetic or real. Real data are either experimental data reported in the literature
and laboratory archives [60–63] or measured (either experimentally or operationally in the
field). On the other hand, synthetic data can be generated using numerical models. For
instance, finite element analysis is the method often preferred for structural engineering
applications [64].
Since its introduction and successful commercialization in the 1950s, the FEM has
undergone rapid development. Compared to alternative numerical approaches, the FEM
enjoys broader usage across a diverse array of applications, where ample data are avail-
able [65]. The simplicity of managing complex geometries and boundary conditions con-
tributes significantly to the widespread adoption of this approach. Moreover, as the finite
element mesh is refined, the accuracy of the solutions improves correspondingly. Therefore,
the convergence behavior serves as a critical aspect in guaranteeing solution reliability.
A large number of applications in structural mechanics, fluid dynamics, electromag-
netics, and various engineering domains rely on FEM for solving boundary value problems.
The approximate solutions to the corresponding partial differential equations are computed
at discrete points across the computational domain by analyzing the resulting linear al-
gebraic system [65]. For time-domain problems, time-stepping schemes are sometimes
necessary for time integration, requiring the solution of the resulting linear system at each
time step. The size of these systems can be exceptionally large, ranging from millions to
billions of degrees of freedom, and simulation times on cluster machines or supercomputers
can vary from hours to days or even weeks. Additionally, even minor adjustments to input
parameters necessitate repeating simulations from scratch. Recent advancements in SML
algorithms and their successful integration across various domains indicate that, when
appropriately selected and trained, these models can significantly enhance conventional
methodologies (e.g., the FEM) [65].
The SML algorithm can then learn from the synthetic data to efficiently predict the
numerical solutions for new cases [64,66]. However, models developed with synthetic
data such as those from finite element analysis are often approximations of real-world
scenarios and are liable to underperform in real-world applications where common sce-
narios involve a large number of variables, substantial uncertainty, and rapid behavioral
changes [67]. Hybrid datasets, a combination of synthetic and experimental datasets,
have been suggested [67,68] for the purposes of making the models more reliable for
real-world applications.
Despite the scalability of linear solvers, finite element models demand substantial
computational resources, and aside from the final results, any knowledge gained by the
machine during the simulation is lost. Adjusting input parameters even slightly or re-
producing studies conducted elsewhere typically necessitates repeating time-consuming
analyses from scratch. Conversely, appropriately discretized physical systems yield highly
accurate finite element results, which can be utilized alongside input parameters to train
SML models [69]. An efficient approach involves training the model on large datasets
generated by well-established conventional FEM tools across random fundamental prob-
lems [70]. Additionally, training data can be augmented by actual measurements and
simulation outcomes for real-world problems shared among users of FEM packages [71].
Notably, when appropriately trained, such models can find utility across a broad spectrum
of applications.

2.2. Computational Mechanics

SML has recently found applications in computational mechanics, including the
formulation of multiscale elements [65,72], enhancement of traditional elements [73], and
development of data-driven solvers [74]. For instance, Capuano and Rimoli [65] employed
ML techniques to devise a novel multiscale finite element algorithm known as the smart
element, which is noted for its low computational cost. This approach utilizes ML to
establish a direct relationship between the computational domain state (outputs) and
Buildings 2024, 14, 3515 8 of 36

external forces (inputs), thereby circumventing the complex task of determining the internal
displacement field and eliminating the need for numerical iterations. The solution of
ordinary differential equations (ODEs) and partial differential equations (PDEs) using
neural networks has been investigated in several previous studies [75–77], focusing on
shallow neural networks and fixed meshes for approximation. With recent advancements
in deep learning, there has been a growing interest in the development of unstructured ML-
based solutions for ODE and PDE approximation [78–84]. Many of these methodologies
solve ODEs or PDEs by randomly sampling points in the domain, defining a loss function
as the summation of residuals for governing equations and boundary conditions, and
employing deep neural networks (DNNs) for solution approximation. Saha et al. [85]
constructed a hierarchical deep learning neural network by creating structured DNNs. This
neural network accepts nodal coordinates as input and generates associated global shape
functions with compact support through a neural network whose weights and biases are
solely determined by the nodal positions [85].
One of the primary challenges encountered when employing SML approaches is the
convergence of approximation errors to acceptable values, which typically necessitates a
substantial volume of data. However, acquiring such data for complex models utilizing
the FEM can be arduous and costly. To mitigate the data requirements of training ML
algorithms, researchers in [86] have developed physics-informed or physics-based learning
techniques. The underlying hypothesis posits that encoding information based on the
inherent physics of the system can reduce the data necessary for ML algorithm learning.
Raissi and Karkiadakis [87] demonstrated that incorporating physics-based information,
such as corotational displacements, significantly diminishes the requisite number of train-
ing samples. Physics-based ML presents a promising avenue, necessitating the utilization
of governing partial differential equations to guide the ML algorithm. Badarinath et al. [88]
introduced a surrogate finite element approach leveraging ML to predict the time-varying
response of a one-dimensional beam. Various ML models, including decision trees and
artificial neural networks (ANNs), were developed and compared in terms of their perfor-
mance for directly estimating stress distribution across a beam structure. Surrogate finite
element models based on ML algorithms demonstrated the ability to accurately estimate the
beam response, with ANNs yielding the most precise results. However, Hashemi et al. [89]
showed that ML-based surrogate finite element models that use extreme gradient-boosting
trees outperform other ML algorithms in predicting the dynamic response of an entire 2D
truss structure. Consequently, the efficacy of surrogate models relies not solely on the ML al-
gorithm employed but also on problem conceptualization and approximation. Furthermore,
Lu et al. [90] showcased a deep neural operator surrogate model for predicting transient
mechanical responses of an interpenetrating phase composite beam comprising aluminum
and stainless steel under dynamic loading. The deep neural operator comprises two feed-
forward neural networks: a trunk net and a branch net, whose matrix product learns the
mapping between nonlinear operators. The deep neural operator is deemed robust and
potentially capable of yielding extended-time predictions if appropriately trained [90].
Li et al. [91] used graphical neural networks (GNNs) for predicting structural responses
(displacement, strain, stress) under dynamic loads. The motivation is that GNNs use an
iterative rollout prediction scheme that captures the spatial/temporal dynamics of the
structure while being computationally efficient. The approach was implemented to study
the structural response of a metal beam, but its scalability has not been demonstrated for
larger structures. To account for local nonlinearities in structural systems (e.g., at joints or
interfaces), Najera-Flores et al. [92] proposed a data-driven coordinate isolation technique
to isolate the nonlinearities and reintroduce their effect as boundary traction. This, coupled
with a structure-preserving multi-layer perceptron and boundary measurements only can
record the dynamics of the original system.
Finite element solutions depend on domain geometry and material properties, and
under specific conditions, solution convergence may degrade due to shear locking [69].
To mitigate locking effects, bending modes can be incorporated according to bending
Buildings 2024, 14, 3515 9 of 36

directions, and analytical bending strains can be enforced using an assumed strain method.
Optimal bending directions for a given element geometry, material properties, and element
deformation are determined to minimize element strain energy. Deep learning is employed
to address the time-consuming task of searching for optimal bending directions [93]. This
approach offers the advantage of deriving highly accurate finite element solutions even
with coarse and severely distorted meshes. Despite its versatility, the FEM can become
computationally prohibitive in various scenarios, including problems with discontinuities,
singularities, and multiple relevant scales. ML, when combined with numerical solutions,
can help alleviate this limitation. For example, Logarzo et al. [94] used ML to homogenize
the models of microstructures and produce constitutve laws that can handle nonlinearities
and path dependency. The resulting constitutive models could also be integrated into
standard FE models and be used to analyze stresses at the level of engineering components.
Conversely, Brevis et al. [95] expanded upon the work presented by Mishra [96] through
exploring the acceleration of Galerkin-based discretization using ML, specifically the FEM
for approximating PDEs. Their objective was to achieve accurate approximations on coarse
meshes, effectively resolving quantities of interest.

2.3. Structural Health Monitoring

The structural health monitoring (SHM) process typically entails globally observing
a structure or system through measurements, extracting damage-sensitive features from
these measurements, and statistically analyzing these features to assess the current state of
the structure or system [97]. When continued over a long time period, the SHM process
provides updated information on the present state of the structure, taking into account
factors such as aging and damage accumulation resulting from the structure’s operational
environment. For discrete events such as earthquakes and bombings, SHM can be used for
a rapid structural integrity screening [97,98].
SHM for civil infrastructures such as bridges, tunnels, dams, and buildings arose
from the need to supplement intermittent structural maintenance and inspections with
continuous, online, real-time, and automated systems [99]. Unlike aerospace structures,
civil infrastructures are mostly distinct and unique from one another. Thus, a major
problem in the SHM of civil infrastructure is the need for long-term evaluation of the
structure’s undamaged or healthy state [99]. Other challenges with civil infrastructure
damage assessment include the physical size of the structure, variability in operational
environments, optimal definition and location of sensors for measurements, identification
of damage-sensitive features (especially features sensitive to small damage levels) [97], the
ability to differentiate between features sensitive to changes in environmental conditions
from those caused by damage, and the development of statistical methods to differentiate
between damage and undamaged features [97].
Present-day SHM for civil infrastructures evolved from activities that used to be
known as structural monitoring, structural integrity monitoring, or simply monitoring [99].
Today, the aim of SHM for civil infrastructures has broadened to the development of
effective and reliable means of acquiring, managing, integrating, and interpreting structural
performance indices with the aim of extracting useful information at a minimum cost with
less human intervention [99]. SHM for civil infrastructures at its core employs continuous
time-dependent data from either physical or parametric models of the structural system
measured from vibrations or slowly changing quasi-static effects such as daily thermal
changes in the structure [99]. For civil engineering infrastructures, vibration-based damage
assessment for bridges and buildings is based on changes in the modal properties of
the structure [97,100]. The overarching aim of vibration-based SHM is the monitoring
of structural conditions by observing changes to the structural behavior to rapidly and
robustly detect structural damage [101]. Initially, there was not much optimism towards
real-time component-level damage identification, location, and quantification for civil
infrastructures based on vibration studies [99]. Significant progress in civil infrastructure
SHM began more as a result of legislation and legal requirements for major construction
Buildings 2024, 14, 3515 10 of 36

projects such as dams and bridges [99]. Much research on civil infrastructure SHM today
now focuses on component-level or real-time damage monitoring.
The application of ML to SHM may be said to find its root in the acknowledgment
that the SHM problem is essentially one of statistical pattern recognition [97]. SHM is a
field that is concerned with the process of online-global damage identification. In SHM,
damage diagnosis is ranked in an ascending order of difficulty: detection, localization,
assessment, and prediction [102]. According to Worden and Manson [102], these levels of
the SHM problem can be posed as either a classification, regression, or density estimation
ML problem. A structural system is said to be damaged when there are changes in the
system that adversely affect its performance. These could be changes in material properties
and geometric properties, boundary conditions, and system connectivity [97]. These
changes necessitate a comparison between two system states (damaged and undamaged
state) for damage identification. The changes are most often recorded as changes in the
dynamic response of the structure or system under consideration [97]. Damage may be
progressive and occur over a time period, such as fatigue and corrosion, or it may result
from independent events such as earthquakes, explosions, or fire. Damage may progress
from a material defect to a component failure under certain loading conditions and then to
system-level damage. A damaged system still retains functionality, whereas failure occurs
when damage progresses to the point of total loss of system functionality.
According to Farrar et al. [103], SHM as a statistical pattern recognition problem can
be distilled into the following four steps: operational evaluation, data acquisition, normal-
ization and cleansing, feature selection and information condensation, and statistical model
development for feature discrimination. The foremost step, the operational evaluation
stage of the process, seeks to define the system’s damage possibilities, operational and envi-
ronmental conditions for monitoring the system, and possible limitations to monitoring the
system [103]. At the statistical model development stage, damage feature discrimination
is achieved using supervised learning by means of classification or regression when both
damage and undamaged data are available [97]. Supervised ML models are better used to
determine the type of damage, the extent of damage, and the remaining useful life of the
system [97].

2.3.1. Utilizing Machine Learning

In an early work on ML-based structural health monitoring (SHM), Yeh et al. [104]
developed an ML model for diagnosing damage to prestressed concrete piles based on data
collated from interviewing several human experts in the field. Advances in computing
and sensing devices have created more robust approaches for data collection in damage
diagnosis using supervised learning. Supervised ML algorithms have contributed to SHM
in buildings [105,106], bridges [107–109], and dams [110–113]. SML algorithms have been
used to monitor flow leakages [112], displacements [110], pore pressure [111], and to
determine seepage parameters [113] in dams. In [105], derived the first flexural modes
of a five-story building from a finite element model, and used them as input to a neural
network to determine damage in the structure. The trained neural network outputs the
mass and stiffness of the structure, which are used to determine a damage index for the
structure. Chang et al. [106] applied the same approach to a seven-story building and to a
scaled twin-tower to detect, localize, and appraise damage to the structure.
Recently, transfer learning (TL) has emerged as an important machine learning method-
ology for SHM. As the name implies, TL is an ML methodology that attempts to transfer
knowledge or experiences gained from learning to perform one task to a different but
related task [114,115]. Knowledge from a source task is used to improve the training of a
related but different target task. The success of a transfer is dependent on the existence
of sufficient commonality between the source and target tasks. Generally, it has been
recommended as a solution for machine learning applications where data labeling is not
achievable and capturing unlabeled data is difficult as well [115]. The learning experience
Buildings 2024, 14, 3515 11 of 36

from the source task can be used to reduce the amount of labeled and unlabeled data
required for a target task.
One of the challenges for data-driven SHM is the unavailability of labeled damage
data due to the difficulties associated with obtaining damage data for large civil infrastruc-
tures [116]. Gardner et al. [116] applies heterogeneous TL by means of utilizing labeled
damage data over a wide range of damage states from a population of similar structures for
data-driven SHM for a structure of interest. This population-based SHM (PBSHM) provides
an alternative to SHM unsupervised learning approaches, i.e., novelty detection. The het-
erogeneous transfer learning is achieved by means of kernelized Bayesian transfer learning
(KTBL), which is a supervised learning algorithm that leverages information across multi-
ple datasets to create one generalized classification model. Gosliga et al. [117] also applied
PBSHM in the absence of labeled damage data for bridges. Bao et al. [118] combined TL
with deep learning approaches. Using data from physics-based (FE-model) and data-driven
methods, Gosliga et al. [117] showed that structural condition monitoring can be carried
out with limited real-world data. They demonstrated this approach with vibration-based
condition identification for steel frame structures with bolted connection damage. Their
results showed that TL yielded higher identification accuracies. Tronci et al. [101] also used
the concept of TL to detect damage-sensitive features from vibration-based audio datasets
of Z24 bridge experimental data. This was carried out to also show that TL can be used to
mitigate the unavailability of labeled data for damage assessment [101].
TL can be carried out by means of full model transfer [119] or by transferring a
portion of the model [120]. Li et al. [119] applied TL by means of model transfer in
combination with deep learning using a convolutional neural network to predict dam
behavior. Model transfer is used to reduce training time and improve the performance
of the model. Tsialiamanis et al. [120] applied TL by transferring a fixed trained batch of
neural network layers trained to localize damage for simpler damage cases to help with
feature extraction for difficult cases. TL has also been recommended for SHM of composite
structures [121].
Innovative approaches to SHM have been presented by researchers recently. An SHM
decision framework applicable to real-world structures to determine whether or not to
install vibration-based SHM on a structure has been developed [122]. This framework,
in essence, quantifies the value of vibration-based SHM on the basis of the difference
in total life-cycle costs and is applicable to a variety of use cases across different time
scales. It also covers models for inspection and maintenance decisions throughout a
structural life-cycle. The framework uses a Bayesian filter for joint deterioration parameter
estimation and structural reliability updating using monitored modal and visual inspection
data. Markogiannaki et al. [123] proposed a framework for damage localization and
quantification that is model-based rather than data-driven approaches and uses output-
only vibration measurements. They use the FE model and FE model updating techniques
to obtain the representative numerical model of the structural system.

2.3.2. Digital Twins

The concept of digital twins has been much welcomed by the SHM community. It
has been considered a potentially transformative concept in modeling and simulation
for engineering applications [100]. A digital twin represents a virtual replica of a system
constructed through a combination of algorithms and data. One significant advantage of
digital twinning lies in its potential to enhance predictive capabilities. It is envisaged that
digital twins will find utility in modeling systems where physics-based models encounter
considerable epistemic uncertainty [100]. However, the field of engineering dynamics
presents challenges in developing an efficient digital twin [100]. The components nec-
essary for constructing an effective digital twin can be categorized into physics-based
modeling, verification and validation, data-enhanced modeling, software integration and
management, uncertainty quantification, and output visualization [100]. Wagg et al. [100]
showcased the synthesizing process and challenges of the development of an effective
Buildings 2024, 14, 3515 12 of 36

digital twin for SHM via the use of a three-story structure. The structural model is de-
terministically calibrated, validated, and tested to perform as a digital twin. It performs
well on test data but fails on new data that introduces non-linearity into the structural
model. Improvement in the predictions of the model is observed after data augmentation
is introduced into the model by means of a Gaussian process ML. This goes to show the
value of data augmentation in the development of digital twins.

2.4. Structural Design and Manufacturing

The structural design process for buildings often consists of decisions on the build-
ing shape, the number and connectivity of structural members, and the sizing of these
members [124]. ML algorithms have been proposed for the optimization of either one
or a combination of these processes. In the design conceptualization stage, the building
floor plan largely forms the building shape. Chaillou [125] used a conditional Generative
Adversarial Network (cGAN) in a picture-to-picture mapping to generate building floor
masterplans. Although this work is currently at the forefront in this domain, it is limited by
the discontinuity of structural load-bearing walls from one floor to the next. The output,
also being an image file, would require transforming the image outputs into usable design
drawings. It should also be emphasized that the work of Chaillou [125] is targeted for
use by architects. Ampanavos et al. [126] carried out similar work using a convolution
neural network for the development of structural floor layouts in the initial design phase.
Rasoulzadeh et al. [127] sought to fully integrate early design stage workflows between
architectural, engineering, and construction teams with a 4D sketching interface that com-
prises geometric modeling, material modeling, and structural analysis modules. The three
modules create a framework for reconstructing architectural forms from sketches, predict-
ing the mechanical behavior of materials, and assessing the form and materials based on
finite element simulations. It should also be noted that the work in [125,126] is focused
on steel frame structures that have a smaller design space (available steel sections) when
compared to reinforced concrete structures. Researchers in [124,128–130] have focused on
reinforced concrete and worked on the layout optimization, sizing, and design of shear
walls using several supervised ML algorithms. For example, the work in [131,132] pro-
posed the automation and optimization of building design processes. Researchers have also
studied ML applications in prestressed concrete [133], masonary arches [134], estimation of
embankment safety loads [135], and steel connection behavior [67].
To produce high-quality and cost-effective structural elements, it is essential to de-
velop the manufacturing and production techniques of these elements. In this context,
the cutting force plays a crucial role. Incorrectly selected cutting conditions can lead to
intensive stress fields in the cutting zone, resulting in excessive tool wear, diminished
accuracy, and a decline in part quality [136]. Furthermore, modeling the milling process
has been a significant area of research for many years, driven by the increasingly strin-
gent industrial demands and standards necessary to ensure the quality of manufactured
elements. Therefore, research and development efforts are vital to obtaining numerical
and statistical approximations of the milling process, aimed at elucidating the phenomena
occurring during cutting and predicting manufacturing process quality. It is noteworthy
that the majority of milling force models are either analytical [137], empirical [138], or based
on finite element analysis [139,140]. Charalampous [141] employed ML in conjunction with
finite element models to predict cutting force during the milling process relative to cutting
speed. Experimental results from milling investigations were filtered and inputted into ML
algorithms to develop reliable predictive models. The study concluded that ML models
can accurately estimate the intricate interactions between cutting conditions and resulting
cutting forces [141].
ML applications in additive manufacturing have attracted considerable attention from
researchers. Jirousek et al. [142] explored the relationship between design parameters of
additively manufactured auxetic structures and target properties using machine learning
algorithms. Employing Shapley Additive Explanations, the study [142] reveals that strut
Buildings 2024, 14, 3515 13 of 36

thickness is the critical parameter affecting the Poisson’s ratio of auxetic structures. The
orthotropic mechanical behavior of components poses a challenge in additive manufac-
turing due to its layer-by-layer fabrication process. Grozav et al. [143] utilize ANNs to
predict mechanical properties at various orientation planes of components affected by
the layer-by-layer fabrication process. The findings from their research show promise in
addressing components prone to orthotropic behavior.

2.5. Stress Analysis

Stress analysis constitutes a cornerstone of structural engineering, representing a
dynamic area of research. Numerical analysis methods, such as the FEM, are utilized for
stress analysis of intricate structures and systems where obtaining an analytical solution
may prove challenging. The finite element analysis (FEA) serves to assess the stress for
design, maintenance, and safety of complex structures across various applications, includ-
ing aerospace, automotive, architecture, and more recently, biomedical engineering [144].
However, dealing with highly nonlinear problems can be a major computational burden for
the method. For example, advancements in imaging techniques have facilitated the study
of human tissues and organs using biomechanics to develop patient-specific treatment
strategies, which has exposed certain limitations for the FEA [69,144–146]. In this regard,
SML algorithms show strong potential in providing approximate stress analysis results as
accurate as those obtained via numerical methods such as the FEM but using significantly
fewer computational resources [64,66,88,147,148]. Furthermore, the algorithms presented
in [64,66,147] leverage image processing techniques to reduce the computational burden
of nonlinear stress analysis using numerical methods. Indeed, it was even possible to
achieve stress predictions in real-time using surrogate finite element analysis and SML, as
demonstrated in [88]. Such developments clearly reflect the potential SML has in the future
for stress analysis.

2.6. Failure Analysis

In recent years, SML-based approaches have garnered significant attention for their
capability to reduce the computational burden associated with fatigue assessment. Yan
et al. [149] developed an ANN using a dataset comprising numerous crack patterns of
reinforced concrete slabs and their corresponding fatigue life. This neural network was
utilized to establish a relationship between the fatigue life of bridge decks and the observed
surface cracks, enabling quick and quantitative predictions of bridge fatigue life. The study
detailed in [149] investigated the fatigue failure reliability of a typical composite steel girder
bridge under vehicular overloading conditions. Initially, deterministic simulations were
conducted to obtain bridge responses under overloading scenarios, considering overloaded
trucks based on axle load and gross weight. To circumvent time-consuming FEA simula-
tions, a feed-forward neural network was trained, validated, and tested. Subsequently, the
trained ANN was combined with the Monte Carlo method to predict the fatigue failure
probability of steel girder bridges under traffic overloading. Additionally, Reiner et al. [150]
developed an ANN surrogate model for simulating progressive damage in fiber-reinforced
composites. To address uncertainties and variations in material properties, they incor-
porated a Markov Monte Carlo Chain as a Bayesian parameter estimator for their input
parameters. To overcome the limitations of classical models in estimating fatigue crack
growth, interdisciplinary methods are being introduced. Numerical approaches and ML
methods are commonly employed and have demonstrated effectiveness. Furthermore,
combining numerical approaches with SML algorithms represents an important research
direction. For instance, knowledge-based neural networks can be integrated with FEM and
optimization algorithms [151].
While numerical approaches typically simulate fatigue crack growth processes along-
side classical models, ML methods offer a flexible and alternative approach due to their
capability to approximate nonlinear behavior and multivariable learning ability, rendering
them promising and advanced methods for such applications [152]. Moreover, various algo-
Buildings 2024, 14, 3515 14 of 36

rithms are employed in data-driven systems within this context, including support vector
machine (SVM), genetic algorithms (GAs), ANN, fuzzy logic, neural–fuzzy systems, and
particle swarm optimization (PSO) [153]. Using the particle swarm optimization–extreme
learning machine (PSO-ELM) algorithm, Yu et al. [154] achieved the evaluation and detec-
tion of rail fatigue crack depth with an accuracy exceeding 99.95%. The extreme learning
machine is a supervised ML algorithm for training single hidden layer feedforward neural
networks (SLFNs) and is noted for its faster convergence compared to conventional neural
network algorithms. The remarkable learning and generalization abilities of ML enable it to
model internal connections and tendencies from complex or imprecise data. Consequently,
ML methods find applications in various facets of fatigue research [155].
In contrast, Zio and Maio [156] utilized the relevance vector machine (RVM) to predict
the remaining useful life of a structure. Their application exhibited good agreement with the
model-based Bayesian approach for predicting fatigue life in aluminum alloys. However,
their study did not assess the method’s applicability to different materials. Meanwhile,
Mohanty et al. [157] employed the radial basis function network, an ML algorithm, to
model fatigue crack growth. The method demonstrated strong applicability across various
aluminum alloys. Nonetheless, a thorough investigation into the differences between
different ML algorithms in fatigue crack growth calculation is lacking, making it challenging
to determine the most suitable algorithm for fatigue crack growth prediction. The radial
basis function network (RBFN) is one such ML algorithm that employs multidimensional
spatial interpolation techniques. It can utilize various learning algorithms based on different
methods for selecting the center of the activation function. The RBFN can be trained more
rapidly than the backpropagation network and is capable of handling nonlinear problems
with complex mappings [158,159]. Moreover, it has been shown to be effective for fatigue
crack growth under both constant and variable amplitude loadings, as it can predict residual
stresses following the shot-peening process using supervised learning supplemented by
continuous learning.

2.7. Material Modeling

SML-based material models have been proposed for use within FEM [160]. Hashash
et al. [160] formulated the material stiffness matrix from a ML material model for use
within FEM. The neural network material model provided a stress–strain relationship
from which the implied material stiffness matrix could be extracted. Carneiro et al. [161]
trained a ML-based material model to approximate the stress–strain relation that can be
obtained from the finite element model of the raw material microstructure or representative
volume element (RVE). They analyzed critical macroscopic points where high-fidelity
models would be necessary for path-independent materials at large strains. Also, using
RVE and deep machine learning, Nikolic et al. [162] modeled temperature-dependent stress–
strain hardening curves for material microstructure. The accuracy of ML material models,
just like other ML models, depends quantitatively and qualitatively on the provided
data [60,160]. In fact, data for developing an ML material model should capture all aspects
of the material behavior to be meaningful. SML-based material models, such as those
in [161–163], approximate material behavior based on the dataset used in developing the
model. Oladipo et al. [68] developed an SML model for the design and development of
metamaterials based on a hybrid dataset combining numerically simulated results with
experimental results. The hybrid dataset is chosen to improve the reliability of the model.
They also incorporated Shapley Additive Explanations (SHAPs) to make the SML model
interpretable. Long et al. [164] used SML to quantify the effect of structural characteristics
of foam structures on their thermal conductivity.
Recently, interest has developed in modeling the behavior of granular materials [165–167]
using deep learning algorithms such as recurrent neural networks (RNNs) and convolutional
neural networks (CNNs). Gang et al. [165] used long short-term memory networks, a class of
RNN algorithms, due to the path/history dependency of granular material behavior. Concrete,
being a complex material, has attracted the attention of ML researchers from the early days of
Buildings 2024, 14, 3515 15 of 36

ANNs [60–63]. The ML models for predicting the compressive strength of concrete have been
quite popular [63,168–174]. Hakim et al. [168] reported error levels in the strength prediction
that are acceptable in concrete technology. Yang et al. [174] used gradient boosting with
categorical features support to enhance the prediction of the compressive strength of concrete.
Robertson et al. [173] incorporated the thermal history of concrete into the features of the
network’s input in addition to the inputs for the mix components. Thermal history is recorded
through curing inputs such as specimen maturity, maximum temperature encountered during
curing, and the duration of maximum temperature exposure. The study highlights that input
analysis revealed strength predictions to be more sensitive to curing inputs compared to
mixture inputs [173].

2.8. Optimization Problems

Genetic algorithms (GAs) represent a form of evolutionary algorithms characterized by
symbolic optimization. Within genetic programming, binary trees are commonly utilized
to depict candidate structures, with diverse hierarchically structured trees constituting the
population. Once the evolutionary process commences, it involves selection, crossover,
and mutation operations [175]. The symbols and variables at each node can be modified
through crossover and mutation. GAs have found extensive application in exploring
the relationship between independent and dependent variables, owing to their simple
and explicit expressions that offer clear explanations, such as in predicting soil physical
indices [176]. Furthermore, they have been advocated as an optimization tool within FEA
packages for structural design [177]. However, genetic programming heavily relies on
stochastic procedures and operators, and the multitude of potential initial population
combinations may become relatively vast [178].

2.9. Summary and Outlook

SML is one of the most widely adopted approaches in ML approaches to structural
engineering, particularly in applications involving prediction and classification tasks. This
review covers most of the well-known applications using SML as shown in Figure 5.

Summary: Supervised Machine Learning Applications

APPLICATIONS ADVANTAGES
• Formulating multiscale elements • Reducing computational cost
Computational • Enhancing the performance of traditional elements
mechanics • Eliminating the need for iteration calculations
• Producing data driven solvers • Increase the computational accuracy
Damage detection, localization and assessment in • Rapid evaluation of the safety and integrity
Structural Health • Buildings of infrastructures
Monitoring • Bridges • Early detection and assessment of damage
• Dams

• Studying the cutting forces applications • Improve decision making

• Milling Processes • Reduce operational cost
Manufacturing & • Architectural and structural floor layouts • Reduce architectural and structural back
Structural Design
• Design of structural elements and forth in early design stages
• Optimization of design processes • Faster design turn around time
• Real-time stress prediction • Reduce computational cost
Stress Analysis Reduce computational effort
• Nonlinear stress analysis •
• Prediction of fatigue life • Reduce computational effort
Failure analysis • Fatigue crack growth rate • Flexibility in fatigue crack growth rate
• Predicting the remaining useful life of a structure modelling
• Formulation of material stiffness matrix • Faster determination of material behaviour
Material • Development of material models and properties
Modelling
• Prediction of concrete compressive strength

Figure 5. Summary of SML applications.

SML methods require labeled data, allowing algorithms to learn from input–output
pairs and develop a mapping function. Despite its effectiveness, SML faces several chal-
lenges. One major limitation is the dependency on high-quality labeled data, which can be
both time-consuming and costly to obtain. Furthermore, models developed through SML
often exhibit a propensity for overfitting, especially when trained on limited datasets [179].
Buildings 2024, 14, 3515 16 of 36

Additionally, SML techniques can be sensitive to the quality and distribution of training
data, leading to inadequate generalization when applied to unseen scenarios. Many exist-
ing SML methods operate as “black boxes”, offering little insight into their decision-making
processes. This lack of interpretability poses challenges in critical applications where
understanding model behavior is essential.
Future research in SML should focus on enhancing model transparency, developing
algorithms capable of learning from fewer labeled examples, and improving generalization
capabilities across diverse applications in structural engineering.

3. Unsupervised Machine Learning Applications

Unsupervised Machine Learning (UML) is a highly interdisciplinary field that draws
upon concepts from statistics, computer science, engineering, optimization theory, and
various other scientific and mathematical disciplines. Gharahamani [180] provides a
tutorial and overview of UML from a statistical modeling perspective. UML methodologies
often draw inspiration from Bayesian principles and information theory. Foundational
models within UML encompass state-space models, factor analysis, hidden Markov models,
Gaussian mixtures, independent component analysis, principal component analysis, and
their respective extensions [180]. The expectation-maximization algorithm is pivotal in
this domain, along with fundamental concepts such as graphical models and graphical
inference algorithms, which are elaborated on by Le [10]. Moreover, Le [10] provided a
concise overview of approximate Bayesian inference techniques, which include methods
such as Markov Chain Monte Carlo, variation approximations, expectation propagation,
and Laplace approximation.
In general, UML can be especially challenging when working with large sets of data.
For example, two prominent techniques in UML, namely Deep Belief Networks (DBNs)
and sparse coding, are often too slow for large-scale applications and are thus primarily
focused on smaller-scale models [22]. Massively parallel methods have been employed to
address these scalability issues [15]. Additionally, the computational capabilities of modern
graphics processors surpass those of multi-core central processing units (CPUs), thereby
enhancing the applicability of UML methods. General principles for massively parallelizing
UML tasks have been developed using graphics processors, and these principles are
applied to both DBNs and sparse coding to scale and optimize learning algorithms [22].
Implementations of DBNs have demonstrated speedups of over 70 times compared to
dual-core CPU implementations for large models.
Locally linear embedding (LLE) emerges as a UML algorithm that operates without
requiring labeled data inputs or feedback from the learning environments. A comprehen-
sive survey of the LLE algorithm, including implementation details, potential applications,
extensions, and its relationship to different eigenvector methods used for nonlinear dimen-
sionality reduction and clustering, is provided in [181].
It is noteworthy that UML algorithms may attempt to tackle specific tasks in a more
challenging manner than necessary or even address the wrong problem altogether, which
is a common criticism. Nonetheless, LLE addresses many of these critiques, distinguishing
itself within a novel category of UML algorithms marked by global optimization strate-
gies, straightforward cost functions, and pronounced nonlinear dynamics without strong
parametric assumptions [181]. These algorithms are expected to find broad usage across
various fields of information processing, particularly as tools to streamline and expedite
other machine learning techniques in high-dimensional spaces.

3.1. Cluster Analysis

Cluster analysis, a fundamental method for understanding and learning, organizes
data into meaningful groupings based on similarities and characteristics, without using
category labels or prior identifiers such as class labels. Data clustering is characterized
by the absence of category information and aims to uncover structure within data, with
a long history in scientific research [22]. The k-means algorithm, introduced in 1995,
Buildings 2024, 14, 3515 17 of 36

stands out as one of the most popular and straightforward clustering algorithms. Building
domain-specific search engines represents a significant application of UML. These search
engines offer highly accurate results with additional features not available in general
web-wide search engines but can be challenging and time-consuming to develop and
maintain. To address this challenge, UML techniques have been proposed to automate
their creation and maintenance, enabling quick and efficient development with minimal
effort and time investment [182]. The emphasis is on topic-directed spreading, such as
substring extraction for relevant topics and constructing a hierarchy of browsable topics. By
leveraging unlabeled data such as class hierarchies and keywords, the burden on classifiers
is reduced. Instead of handling labeled training data, the builder provides a set of keywords
for each category, which can serve as a rule for list classification.
Recent advancements in latent class analysis and associated software provide an alter-
native avenue to conventional clustering methodologies such as k-means, accommodating
continuous variables. A comparative evaluation of the two approaches is conducted via
data simulations wherein true memberships are identifiable. Parameters conducive to
k-means are selected based on assumptions inherent in k-means and discriminant analysis.
Typically, clustering techniques do not leverage data pertaining to true group memberships.
However, in discriminant analysis, the dataset is initially utilized, serving as a gold stan-
dard for subsequent evaluation. Remarkably, this approach yields significant outcomes,
with latent class performance aligning closely with actual performance under discriminant
analysis, thus blurring the distinction between the two [183].
A novel statistical method, closely linked to latent semantic analysis, has been devised
for factor analysis of binary and count data [184]. In contrast, another method employs
linear algebra by performing Singular Value Decomposition (SVD) of co-occurrence tables.
However, the proposed technique utilizes a generative latent class model for probabilistic
mixture decomposition on the dataset. The extracted results offer a more principled
approach grounded in solid statistical foundations [184]. This technique incorporates
a controlled version concerning temperature and devises maximization algorithms for
model fitting, resulting in highly favorable outcomes in practice. Probabilistic latent
semantic analysis finds numerous applications in natural language processing, text learning,
information retrieval, and machine learning-based applications.

3.2. Data Engineering

UML methods, such as visualization, clustering, outlier detection, or dimension
reduction, are commonly employed as an initial step in data mining to glean insights
into patterns and relationships within complex datasets [185]. Additionally, clustering
can offer preliminary insights into similarity relationships [186], achieved by partitioning
observations into groups (clusters) where observations within clusters exhibit greater
similarity to each other than to those in other clusters [19]. UML methods also find
application in data interpolation techniques, where most extracted data are numerical and
can be interpreted as points in numerical space [17]. Indeed, in cases where only a few
labeled observations are available, a standard approach for estimating model accuracy is
n-fold cross-validation [187]. Maximizing true error, which is the expected error on unseen
observations, provides a better estimation of accuracy on an independent hold-out set not
revealed to the learning algorithm.
Typically, a UML project commences with the preprocessing of raw multidimensional
signals, such as images of faces or spectrograms of speech [19]. The aim of preprocessing is
to derive more informative representations of the information in these signals for subse-
quent operations, including classification, interpolation, visualization, denoising, or outlier
detection [17]. In scenarios where prior information is absent, the aforementioned repre-
sentations must be discovered automatically. This general framework of UML facilitates
the exploration of automatic methods that identify unlabeled structures from the statistical
regularities of large datasets [188].
Buildings 2024, 14, 3515 18 of 36

In data analysis, it is common for the nature or label of the features in data to be
missing or unknown. In such cases, UML algorithms are utilized to explore patterns in the
data. Unlike SML, where a desired output is provided to the network, UML tasks entail
the network discerning patterns in the input independently. To accomplish these tasks,
various UML methods, including frequent pattern detection, clustering, and dimensionality
reduction, are employed [7].

3.3. Feature Engineering

One of the primary challenges encountered in developing an automated feature subset
selection algorithm for unlabeled data involves determining the number of clusters, coupled
with feature selection, as detailed in [47]. Another challenge concerns normalizing the
bias of feature selection criteria with respect to dimensionality. Feature subset selection
is accomplished using expectation maximization clustering, as elucidated in [189], where
two distinct performance criteria are employed to assess candidate feature subsets, namely
scatter separability and maximum likelihood. Dy and Brodley [189] furnished proofs
regarding the dimensionality biases of these feature criteria and proposed a cross-projection
normalization scheme capable of mitigating these biases. Thus, a normalization scheme
was essential for the selected feature selection criterion. It is imperative to underscore
that the proposed cross-projection criterion normalization scheme effectively mitigates
these biases.
The objective of the study presented by Le [10] was to employ UML to construct high-
level, class-specific feature detectors from unlabeled images and datasets. This approach
is inspired by the neuroscientific hypothesis positing the existence of highly class-specific
neurons in the human brain, colloquially referred to as “grandmother neurons”. Contem-
porary computer vision methodologies typically underscore the importance of labeled data
in deriving these class-specific feature detectors. For instance, a large annotated dataset
of images containing faces is typically required to train a face detector, often delineated
by bounding boxes around the faces. However, in scenarios where labeled data are scarce,
significant challenges arise, necessitating large labeled datasets [181].
Cameras that integrate red–green–blue and depth (RGB-D) information provide high-
quality synchronized videos for both color and depth, offering an opportunity to enhance
object recognition capabilities. However, the challenge of developing features for the
color and depth channels of these sensors also intensifies. Liefeng [190] discussed the
utilization of hierarchical matching pursuit (HMP) for RGB-D data. Through sparse coding
facilitated by HMP, hierarchical feature representations are learned from raw RGB-D data
in an unsupervised manner. Extensive experiments across various datasets demonstrate
that features acquired through this approach yield superior object detection results when
employing linear SVM. These findings are promising, suggesting that current recognition
systems could be enhanced without the need for complex manual feature design. Although
the architecture of HMP is manually designed, automatically learning such a structure
remains a challenging and intriguing endeavor.
Approaches that have not demonstrated efficacy in constructing high-level features
often leverage readily available unlabeled data, although they are frequently favored. The
research in the realm of UML is extensive, and while this review addresses certain issues
and applications, Saul and Roweis [188] observed that no single criterion is universally
optimal for all problems. A novel and intriguing perspective is proposed by Dy and
Brodley [189], who advocate for hierarchical clustering for feature selection. However, as
hierarchical clustering yields dataset groupings at multiple levels, UML techniques can
be viewed from the lens of statistical modeling. A coherent framework for learning from
data and for interpretation amidst uncertainty is provided through statistics. Numerous
statistical models employed for UML can be conceptualized as latent variable models and
graphical models, elucidating UML systems for various types of data.
Buildings 2024, 14, 3515 19 of 36

3.4. Structural Health Monitoring

In the absence of damage data, UML models, by means of outlier or novelty detection,
are better used to determine the existence and location of damage [97]. Vibration control,
damage detection, and localization are some of the key areas of UML in structural health
monitoring. Madan [191] used a counter propagation network (CPN) to develop an active
controller against the effect of vibrations caused by seismic ground motions on multi-story
buildings. The CPN is a feature-sensitive ANN that is self-organizing and self-learning. In
the case of SML, a neural network controller is usually trained with known target control
forces for known earthquake ground motions, but in practice, it is difficult to know in
advance the control forces that can produce the best structural response to an unknown
earthquake ground motion. Particularly, without the aid of target or labeled output data,
the system learns by exploiting any pattern or structure within the input data, which
demonstrates the potential of UML in such applications.
The development of supervised damage detectors is usually faced with the unavail-
ability of damage data for large structures as they cannot be intentionally harmed. For
unsupervised damage and anomaly detectors, only undamaged conditions are fed to the
detector, and with the use of a suitable algorithm for feature extraction, damage conditions
can be classified differently and thus detected [192,193]. Researchers in [192] implemented
a nearest neighbor algorithm and in [194], a variational auto-encoder for feature extraction
is used. Note that since no labeled data are needed, this approach is regarded as suitable
for real-life structural health monitoring [194]. Unsupervised learning has been used as
statistical pattern recognition for damage identification and quantification using an autore-
gressive model [195]. Daneshvar and Hassan [196] also employed autoregressive modeling
for feature extraction and then for damage localization using the Kullback–Leibler sta-
tistical distance measure. Nevertheless, the method in [196] revealed that it reduces the
computational cost of data-driven damage localization when dealing with large vibration
data from sensors. Liu et al. [197] used dynamic graph convolutional neural networks
and transformer networks in a unified SHM framework. The motivation for using both
methods is to overcome the challenge of limited labeled data by analyzing sensor-derived
time series data for accurate damage identification. This was coupled with a ‘localization’
score that combines data-driven insights with physics-informed knowledge of structural
dynamics. The framework was validated on various structures including a benchmark
steel structure. Junges et al. [198] convolutional autoencoders and cGANs for localizing
structural damage using Lamb waves without prior feature extraction. The techniques
were validated on two full-scale composite wings subjected to impact damage and both
methods localized the damage with comparable accuracy.
Eloi et al. [199] proposed an unsupervised TL approach for the SHM of bridges. Using
labeled data from FE models as the source domain, they trained classifiers and tested
the performance of these classifiers with unlabeled Z-24 bridge monitoring data (target
domain). Data from both domains are expected to have similar distributions except for
uncertainties in the FE physics-based model of the bridge. Transfer component analysis is
the TL method used in this research and it attempts to transform damage-sensitive features
from the original space to a latent space where the feature distributions are reduced. Bayane
et al. [200] developed five UML algorithms for detecting (in real-time) abrupt changes in
bridges. Part of the study was to investigate the impact of sensor location and types on the
accuracy of damage detection. Lu et al. [201] proposed using bidirectional long short-term
memory networks and a generalized extreme value distribution model to identify and
quantify damage in structures. The proposed methodology was validated using data from
a numerical steel beam model and a real long-span cable-stayed bridge.

3.5. Structural Design and Manufacturing

Various research studies have proposed systematic frameworks based on data mining
to predict the physical quality of intermediate products within interconnected manufactur-
ing processes. Some of these studies delineate data preprocessing and feature extraction
Buildings 2024, 14, 3515 20 of 36

components integrated into the inline quality prediction system, while others demonstrate
the utilization of a combination of supervised and unsupervised data mining techniques to
identify influential operational patterns, promising quality-related features, and production
parameters [202].
The steel industry’s production processes are characterized by resource-intensive,
complex, and automated interconnected manufacturing operations. Technological and
temporal constraints confine product quality assessments to the final production pro-
cess. Consequently, unnoticed quality deviations traversing the entire value chain can
significantly impact failure costs by increasing rejections and interruptions. Hence, novel
solutions for continuous quality monitoring are being explored, particularly in a case study
on hot rolling mills. The aim is to detect quality deviations at the earliest possible process
and in real-time through data mining on distributed measurements across the production
chain. Notably, since the product’s quality depends on its processing, the time series
of measurements recorded at each production stage may contain quality identification
patterns [203]. Furthermore, SML, utilizing quality labels derived from ultrasonic tests, can
develop prediction models capable of forecasting the quality-related physical properties
of a product even at intermediate production stages [204]. Early defect detection will not
only conserve production resources but also promote more sustainable and energy-efficient
interconnected manufacturing processes.
Previous works have addressed distributed data mining and its overarching challenges
concerning sensor data from interconnected processes [203], as well as the issue of acquiring
suitable quality labels [204,205]. Additionally, Konard et al. [204] outlined the deployment
of a data storage and acquisition system, along with the initial prediction outcomes based
on data collected from the rotary hearth furnace.

3.6. Other Structural Engineering Applications

Recently, work has been devoted to the development of PDE solvers without the use
of labeled data [206,207]. Yinhao et al. [207] proposed using physics-constrained deep
learning by means of a convolutional encoder–decoder neural network as a PDE solver
without the use of labeled data. Junho et al. [206] developed an unsupervised PDE solver
adopted from computer vision tasks and requires no training dataset, which they named
the unsupervised Legendre–Galerkin neural network. The solver takes input boundary
conditions and external forces to output numerical solutions of the PDE. This solver is
capable of learning multiple instances of the PDE solutions, unlike most SML solvers, which
only predict a single instance of the solution of the PDE for particular initial conditions,
boundary conditions, and external forces. Piervincenzo et al. [208] developed a UML
algorithm based on outlier analysis for automated fatigue crack detection in structures. In
addition, UML in the form of a fuzzy adaptive resonance theory map was used for the
prediction of the compressive strength of high-performance concrete [62] and recently in
the design optimization of truss structures [209].

3.7. Summary and Outlook

UML is a valuable tool in structural engineering, enabling the analysis of complex
datasets without the need for labeled information. Its applications range from clustering
and dimensionality reduction to anomaly detection, all of which aid in understanding
structural behaviors and identifying patterns that may not be immediately apparent. The
effectiveness of these techniques has been demonstrated in various contexts, including
SHM, material characterization, and design optimization as summarized in Figure 6.
Buildings 2024, 14, 3515 21 of 36

Summary: Unsupervised Machine Learning Applications

APPLICATIONS ADVANTAGES
• Pre-processing of raw multidimensional signals
• Feature selection and extraction • Simplify and accelerate other machine
Feature • Dimensionality reduction
techniques
Engineering • Computational efficiency
• Outlier detection
• Class-specific feature detectors

• Active control against vibrations caused by seismic ground • Reduces computational cost when dealing
motions with large datasets
Structural Health • Feature extraction • Solves the problem of unavailability of
Monitoring • Damage detection damage data for large structures in data-
• Damage localization and quantification driven SHM.
• Real time structural health monitoring

• Identification of significant operational patterns • Early and real-time detection of defects

• Detection of promising quality-related features • Savings in production resources
• Identification of production parameters Sustainable and energy-efficient interlinked
Manufacturing •
• Quality prediction and monitoring manufacturing processes
• Data pre-processing
• Feature extraction

• Data driven solvers without the use of labelled data • Multiple instances of PDE solutions
Other Structural • Fatigue crack detection
Applications • Computational efficiency
• Compressive strength determination

Figure 6. Summary of UML applications.

Despite the significant advancements in UML methods, several challenges remain.

The lack of interpretability in UML algorithms can hinder their adoption in critical ap-
plications where understanding the rationale behind decisions is essential. Additionally,
the performance of UML models can be sensitive to the underlying assumptions made
during the analysis, which may not always align with the complexities of real-world
structural systems.
Looking ahead, further research is required to enhance the robustness and reliability
of UML techniques in structural engineering. This includes developing methods for
better evaluation and validation of UML models, improving algorithms to handle high-
dimensional and noisy data, and integrating domain knowledge to guide the learning
process. Additionally, advancing interpretability techniques will be crucial for building
trust and facilitating the application of UML in practical engineering scenarios.

4. Reinforcement Machine Learning Applications

Due to the nature of RML, this class of ML methods is useful for optimization tasks
and problems that require a dynamic approach. In most engineering applications, the main
goal of RML algorithms is to develop an optimal policy that takes advantage of both the
exploratory and exploitative nature of the reinforcement learning paradigm. The agent
learns from its previous experiences, using them to maximize its reward, and is also able to
develop new solutions by exploring uncharted territory [210]. An agent in a reinforcement
learning network adapts quickly to a changing environment, making it very dynamic. The
behavior of the agent is often partly deterministic and partly stochastic, making the process
of Markov decision an effective formulation for reinforcement learning situations [211].
For complex RML applications that require a lot of training time, especially Markov de-
cision processes (MDPs) that have a large or continuous state, TL has been considered
an alternative for speeding up the training time of the reinforcement learning agent [114].
RML has yielded positive results in decision-making and optimization situations involving
uncertainties, control, and combinatorial explosion problems as the agent learns from its
environment. Popular RML algorithms in research involve the use of Q-learning, adaptive
dynamic programming, temporal difference learning, actor–critic reinforcement learning
networks, and Monte Carlo simulations [212].

4.1. Data Requirement and Preprocessing

Whereas SML requires high-quality labeled data [213,214] and UML requires large
sets of unlabeled data, RML often requires little or no data as an agent learns by trial and
Buildings 2024, 14, 3515 22 of 36

error from its experiences in a dynamic environment. An agent can learn from its environ-
ment without necessarily having prior knowledge of the environment [211,215]. The data
required for reinforcement learning is just enough for the agent to learn how to maximize
its long-term reward. Most RML applications are posed as a Markov decision process
(MDP) [210–212,215], and the MDP is solved when an optimal policy that maximizes the
reward function has been found by the agent. In MDPs, models based on free-reinforcement
learning algorithms require no knowledge of the reward function or the state-transition
probabilities [215], thus reducing the data requirements for model development. It should
also be pointed out that data preprocessing techniques depend on the way a problem is
formulated in reinforcement learning.

4.2. Computational Mechanics

Mesh generation is an important computational process in the development of accu-
rate, stable, and efficient models for structural analysis. By formulating the mesh generation
problem as an MDP, Jie et al. [210] were able to develop a self-learning element extraction
system that automatically generates high-quality meshes (quad meshes) in the boundary
and interior regions of complex geometries. The proposed meshing algorithm is based
on an advantage actor–critic reinforcement learning network. The algorithm is said to
be computationally efficient and reduces the time and expertise required for high-quality
mesh generation. However, it has been shown that it is difficult to mesh geometries with
single-connected domains and boundaries with sharp angles.

4.3. Structural Control

Structural control by means of an RML algorithm has attracted the interest of many
researchers. An early work on structural control using reinforcement learning [216] is a
case-based algorithm where structural control cases are retrieved and adapted to present
control situations based on their past performance. The limitation of this method is that an
extensive number of possible control cases need to be prepared for the model. Much more
recent RML algorithms formulate the control problem as an MDP [211] or use adaptive
dynamic programming [11] or other reinforcement learning methods [217]. RML has
become popular for optimal control strategies, especially for complex and nonlinear systems
with uncertainties and time variations (e.g., where the structure’s parameters or payload
change in time) [215]. It has been used as a control system for the upstream water depth of
a canal [218], to suppress transient vibrations in semi-active structures subject to harmonic
excitation [219], as a vibration control method for a flexible hinged plate [220], in an Internet-
of-Things (IoT)-based bridge structural health monitoring [221], in the structural control of
a floating wind turbine [11], and as an active controller for seismic structures [211,217].
The random nature of earthquake disturbances poses systematic uncertainty for the
control of structures. Online tuning of an active mass drive system using reinforce-
ment learning has been proposed in [217] for the active control of seismic structures.
Arash et al. [217] also incorporated a dynamic state predictor into the reinforcement learning-
based controller to accommodate time delay issues. Soheila et al. [211] have further pro-
posed a scalable form of a reinforcement learning-based active control system that is
applicable to a variety of control mechanisms, linear and nonlinear response regimes, and
several external loadings such as wind, seismic, and other building loads. They also inves-
tigated implementation issues such as sensitivity to variations in structural properties and
time delays. Reinforcement learning has also been studied for implementation in structural
maintenance systems [212,222] and for fault identification [223,224]. An optimal mainte-
nance policy that learns from a bridge’s real historical data [212] and another that seeks to
reduce costs [222] have also been developed. A comparative study of several RML algo-
rithms using a baseline dynamic system (a cart-pole) yielded interesting results [215]. An
actor–critic policy gradient is shown to converge faster with better stabilization compared
to Q-learning in a discrete state-space. In addition, the value-function approximations are
demonstrated to have the best performance.
Buildings 2024, 14, 3515 23 of 36

4.4. Structural Design and Manufacturing

RML algorithms are largely applicable in optimization processes while the use of trial-
based experiments, physics-based simulations, and surrogate models for the optimization of
manufacturing processes is costly, computationally and financially [225]. This is especially
true for new features or process parameter tuning. Compared to surrogate models that are
case-specific, RML algorithms trained on generic data can be used to develop new non-
generic features and process parameters [225]. For large-scale optimization and modeling
of autonomic manufacturing processes, they are incorporated as autonomous decision-
making systems for robotic operators [226]. The robotic operator learns a behavioral
policy that enables it to respond appropriately to variations in its human colleagues and
to adapt itself to changes in observations in its environment and its human counterparts.
The trained robotic operators are then used to reduce system unpredictability caused by
variations in human performance. RML algorithms have been used for general aerodynamic
shape optimization in industrial processes without in-depth knowledge of the domain of
application [227] and specifically as an aerodynamic shape optimizer for seismic-sensitive
structures [228]. They are said to perform better than gradient-based and gradient-free
shape optimization methods [227,228].
RML is imperative for the administration of smart cities based on IoT technology [214,221],
such as in the optimization of traffic in urban centers. The application of RML algorithms in
autonomous navigation has been proposed by several researchers [229,230]. Kevin et al. [230]
used Q-learning for offline path planning for autonomous navigation in static environments,
and in [229], they studied task and path planning in a constrained but dynamic environment.
The work in [229] specifically targeted the assembly and construction of three-dimensional
structures using a reinforcement learning trained quadrotor. The optimal policy in [230] is
based on path length, safety, and energy consumption while in [229], the optimal path is
obtained using a heuristic search method. Structural design, largely being an iterative process,
has attracted the application of RML algorithms. Fabian et al. [231] proposed the use of
RML for data-driven design automation to overcome the challenges of limited sample and
historical design data. They also proposed TL for design tasks using RML. Junhyeon and
Rakesh [232] optimized the design of a truss structure using RML. Maximilian and Gordon [233]
investigated how to further extend structural design synthesis using deep RML to structural
design problems with large state spaces.

4.5. Failure Analysis

Safety assessment often requires the determination of failure modes and stages of
components in a structural system. An often-mentioned problem in the optimization of
failure prediction using data-driven approaches is that of combinatorial explosion when
searching for the dominant failure modes of the structural system [234,235]. Deep RML
was applied to combinatorial explosion, posing the failure component selection process as
a Markov (sequential) decision process [234,235]. Xiaoshu et al. [234] observed the failure
stages and failure components of roof truss and truss bridge structures. They showed that
the deep reinforcement approach is computationally efficient and yields a higher accuracy
than the Monte Carlo simulation and β-unzipping method. The results in [235] show that
the proposed method is applicable to failure analysis of actual structures with significantly
reduced computational cost.

4.6. Material Modeling and Design

RML has been successfully used in material design optimization problems [213,236]
and in dealing with epistemic uncertainty in material models [173]. Johannes et al. [236]
employed a deep Q-network with prioritized experience replay to optimize material design
processing paths. The optimal processing path yielded a target material structure in the
material structure space that delivered a desired set of material properties. Chi-Hua [213]
also used Q-learning to optimize the microstructure and material properties of bio-inspired
composite materials. The RML algorithm is said to have overcome the high dimensionality
Buildings 2024, 14, 3515 24 of 36

problem faced by other optimization methods used in material microstructure design.

Due to the “black box” processing nature of ANNs, predictions are usually made with-
out accompanying confidence levels, which can be dangerous for materials with known
variability such as concrete [173]. Notice that most of the epistemic uncertainty can oc-
cur in a material model due to the unavailability of data on other independent variables
that control the material properties. To address this issue, researchers in [173] introduced
Bayesian variational inference into an ANN for predicting concrete strength by means
of the Monte Carlo dropout method. The Monte Carlo dropout method is incorporated
into the model without additional computational cost. The network weights are randomly
dropped from the neural network during training and testing [213]. This dropout method
introduces model uncertainty into the network. In this manner, the network learns from
the uncertainty in its environment (the layers) while making predictions. However, the
dropout method in this approach does not allow for extrapolation of results outside the
training dataset.

4.7. Summary and Outlook

RML algorithms are suitable for addressing complex optimization problems in struc-
tural engineering as summarized in Figure 7. Its capability to adapt to dynamic envi-
ronments and learn from interactions with them makes RML particularly well suited for
applications involving uncertainties, such as structural control and design. The successful
implementation of various RML algorithms, including Q-learning and actor–critic methods,
has demonstrated their potential to enhance decision-making processes in real-time appli-
cations. However, the effectiveness of RML in structural engineering is often limited by
the availability of high-quality training data and the computational resources required for
extensive training sessions. Additionally, the “black box” nature of many RML algorithms
raises concerns about interpretability and the reliability of their predictions, particularly in
safety-critical applications.

Summary: Reinforcement Machine Learning Applications

APPLICATIONS ADVANTAGES
Computational • Automatic mesh generation • Computational efficiency
Mechanics

• Active Structural control • Optimal control strategy

Structural Health • Structural maintenance systems • Optimal maintenance policies
Monitoring • Fault identification • Dealing with uncertainties systematically

• New features parameter tuning

• Autonomous manufacturing processes • Savings in production resources
• Aerodynamic shape optimization • Quality control
Manufacturing &
• Administration of smart cities based on IoT Technology • Sustainable and energy-efficient
Structural Design manufacturing and construction processes
• Autonomous navigation
• Development of structural design data • Structural design efficiency
• Structural design synthesis

Failure Analysis • Dominant failure modes for failure prediction • Reduce computational cost

• Optimal processing paths in material design processes • Dimensionality reduction

Material Modelling • Material models • Ascertain confidence levels in predictions
• Material microstructure optimization

Figure 7. Summary of RML applications.

There is a need for more research into developing explainable reinforcement learning
models that can provide insights into their decision-making processes. Enhancing the
robustness of these models against variations in environmental conditions and structural
parameters is also crucial. Furthermore, integrating RML with other machine learning
paradigms and domain knowledge could facilitate the development of hybrid models that
leverage the strengths of each approach.
Buildings 2024, 14, 3515 25 of 36

5. Conclusions
This paper presents a comprehensive review of the applications of machine learning
(ML) in structural engineering, examining a diverse array of methodologies and techniques
employed to address highly nonlinear problems in this field. The review categorizes
the methods into three primary types: supervised machine learning, unsupervised ma-
chine learning, and reinforcement machine learning. Each category demonstrates its own
strengths: supervised machine learning excels in regression and classification tasks, un-
supervised machine learning is adept at clustering and uncovering hidden patterns, and
reinforcement machine learning is increasingly favored for automated decision-making
applications. Table 1 provides a summary of the applications and methodologies of ML
techniques reviewed in this paper.
Despite the promising advancements in ML for structural engineering applications,
several challenges persist, including model reliability, uncertainty quantification, robust-
ness, and interpretability. These challenges, although not the primary focus of this review,
represent critical areas for future research aimed at the practical implementation of ML in
real-world engineering problems. These challenges and directions for future research were
highlighted after surveying the applications of each category of ML methods.
This literature review provides a broad overview of the trends in ML applications
within structural engineering, acknowledging the innovative approaches adopted by re-
searchers. The choice of a specific ML method often hinges on the availability of training
data; supervised learning is typically preferred when labeled data is accessible, facilitating
effective predictions and classifications. In scenarios where unlabeled data is abundant,
unsupervised learning techniques play a crucial role in exploratory analysis and anomaly
detection. Meanwhile, reinforcement learning stands out for its ability to optimize actions
in dynamic environments, making it particularly suitable for structural control applications.
Overall, this review underscores the significance of ML in advancing structural engi-
neering practices, offering insights into how these methods can enhance decision-making,
improve model performance, and ultimately contribute to the development of more re-
silient and efficient structures. Future research should focus on overcoming the existing
challenges to maximize the potential of ML in addressing the complexities of real-world
structural engineering scenarios.
Buildings 2024, 14, 3515 26 of 36

Table 1. Summary of ML applications in structural engineering.

Reference Machine Learning Type Focus Area Methodology Potential Applications

[57] Supervised Learning Structural Analysis Finite Element Integration Predicting structural responses
[179] Supervised Learning Damage Detection Neural Networks Real-time monitoring
[66] Supervised Learning Stress Analysis Surrogate Finite Element Models Predicting stress distributions
[103] Supervised Learning Structural Health Monitoring Statistical Pattern Recognition Damage diagnosis and prediction
[125] Supervised Learning Structural Design Generative Adversarial Networks Designing building floor plans
[168] Supervised Learning Concrete Strength Prediction Regression Models Strength prediction in concrete
[174] Supervised Learning Material Properties Gradient Boosting Enhancing prediction accuracy
[143] Supervised Learning Additive Manufacturing Artificial Neural Networks Predicting mechanical properties
[133] Supervised Learning Prestressed Concrete Neural Networks Design and safety evaluations
[173] Supervised Learning Material Modeling Bayesian Inference Predicting concrete strength
[148] Supervised Learning Fatigue Analysis Neural Networks Predicting fatigue life
[134] Supervised Learning Structural Performance Machine Learning Algorithms Analyzing masonry structures
[75] Supervised Learning ODE/PDE solving Neural networks Stress analysis
[76] Supervised Learning ODE/PDE solving Fixed meshes Numerical approximation
[85] Supervised Learning Structural response prediction Hierarchical deep learning Nonlinear dynamics
[58] Supervised Learning Data requirement Dataset analysis Training model efficacy
[59] Supervised Learning Data requirement Quality and relevance of data Model performance
[64] Supervised Learning Data preprocessing Synthetic and real data Stress analysis
[105] Supervised Learning Structural health monitoring Neural networks Damage detection in buildings
[106] Supervised Learning Structural health monitoring Finite element model Damage localization
[107] Supervised Learning Structural health monitoring Neural network Damage detection in bridges
[110] Supervised Learning Structural health monitoring Flow leakage detection Dam monitoring
[111] Supervised Learning Structural health monitoring Pore pressure monitoring Dam safety
[206] Unsupervised Learning Damage Identification Graph Neural Networks Localizing structural damage
[207] Unsupervised Learning PDE Solving Deep Learning Solving partial differential equations
Buildings 2024, 14, 3515 27 of 36

Table 1. Cont.

Reference Machine Learning Type Focus Area Methodology Potential Applications

[180] Unsupervised Learning Data Analysis Clustering Techniques Anomaly detection
[192] Unsupervised Learning Anomaly Detection Variational Autoencoders Structural damage detection
[194] Unsupervised Learning Feature Extraction Nearest Neighbors Monitoring large structures
[22] Unsupervised Learning Clustering Deep Belief Networks, sparse coding Data mining
[181] Unsupervised Learning Dimensionality reduction Locally linear embedding Feature extraction
[206] Unsupervised Learning PDE solving Legendre–Galerkin network Structural dynamics
[207] Unsupervised Learning PDE solving Convolutional encoder–decoder Structural dynamics
[196] Unsupervised Learning Damage localization Autoregressive modeling Damage detection
[200] Unsupervised Learning Bridge Monitoring Dynamic Signal Processing Detecting changes in bridge conditions
[212] Reinforcement Learning Maintenance systems Historical data learning Bridge maintenance
[236] Reinforcement Learning Material design optimization Deep Q-networks Material property prediction
[213] Reinforcement Learning Material modeling Q-learning Material microstructure optimization
[210] Reinforcement Learning Mesh Generation Markov Decision Processes Automated mesh generation
[217] Reinforcement Learning Structural Control Active Control Systems Seismic structure control
[213] Reinforcement Learning Design Optimization Q-learning Optimal design processes
[229] Reinforcement Learning Autonomous Navigation Q-learning Path planning in dynamic environments
[211] Reinforcement Learning Structural Control Actor–Critic Methods Vibration control in structures
[11] Reinforcement Learning Structural Design Dynamic Programming Control of floating wind turbines
[231] Reinforcement Learning Design Automation Deep Reinforcement Learning Data-driven design processes
[234] Reinforcement Learning Failure Analysis Deep Learning Failure mode selection
Buildings 2024, 14, 3515 28 of 36

Funding: The authors gratefully acknowledge the support provided by Qatar University through the
internal grant QUCG-CENG-24/25-449, which has significantly facilitated this research.
Acknowledgments: The authors gratefully acknowledge the support provided by Qatar University
through Collaborative Grant QUCG-CENG-24/25-449. The findings achieved herein are solely the
responsibility of the authors.
Conflicts of Interest: The authors declare that there are no conflicts of interest regarding the publica-
tion of this paper.

References
1. Zhou, L.; Pan, S.; Wang, J.; Vasilakos, V. Machine learning on big data: Opportunities and challenges. Neurocomputing 2017,
237, 350 –361. [CrossRef]
2. Sui, K.; Lee, W. Image processing analysis and research based on game animation design. J. Vis. Commun. Image Represent. 2019,
64, 94–100. [CrossRef]
3. Yang, T.; Cappelle, C.; Ruichek, Y.; Bagdouri, M. Multi-object tracking with discriminant correlation filter based deep learning
tracker. Integr. Comput.-Aided Eng. 2019, 26, 273–284. [CrossRef]
4. Syed, F.; Tahir, M.; Rafi, M.; Shahab, M. Features selection for semi-supervised multi-target regression using genetic algorithm.
Appl. Intell. 2021, 51, 8961–8984. [CrossRef]
5. Wang, P.; Bai, X. Regional parallel structural based CNN for thermal infrared face identification. Integr. Comput.-Aided Eng. 2018,
25, 247–260. [CrossRef]
6. Choppala, S.; Kelmar, T. W.; Chierichetti, M.; Davoudi F.; Huang, D. Optimal sensor location and stress prediction on a plate
using machine learning. In Proceedings of the AIAA SCITECH 2023 Forum, Online, 23–27 January 2023.
7. Badillo, S.; Banfai, B.; Brizzle, F.; Davy, I.; Hutchinson, L.; Kam-Thong, T.; Polster, J.; Steleret, B.; Zhang, D. An introduction to
machine learning. Clin. Pharmacol. Ther. 2020, 107, 871–885. [CrossRef] [PubMed]
8. Karmaker, S.; Hassan, M.; Smith, M.; Xu, L.; Zhai, C. ACM computing surveys. Knowl. Inf. Syst. 2022, 54, 1–36.
9. Laisisi, A.; Attoh-Okine, N. Principal components analysis and track quality index: A machine learning approach. Transp. Res.
Part C Emerg. Technol. 2018, 91, 230–248. [CrossRef]
10. Le, Q. Building high-level features using large scale unsupervised learning. In Proceedings of the 2013 IEEE International
Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 26–31 May 2013; IEEE: Piscataway, NJ, USA,
2013; pp. 8595–8598.
11. Zhang, J.; Zhao, X.; Wei, X. Reinforcement learning-based structural control of floating wind turbines. IEEE Trans. Syst. Man
Cybern. Syst. 2020, 52, 1603–1613. [CrossRef]
12. Jain, A. Data clustering: 50 years beyond K-means. Pattern Recognit. Lett. 2010, 9, 651–666. [CrossRef]
13. Zhang, J.; Xiao, M.; Gao, M.; Chu, S. Probability and interval hybrid reliability analysis based on adaptive local approximation of
projection outlines using support vector machine. Comput.-Aided Civ. Infrastruct. Eng. 2019, 34, 991–1009. [CrossRef]
14. Yu, B.; Wang, H.; Shan, W.; Yao, B. Prediction of bus travel time using random forests based on near neighbors. Comput.-Aided
Civ. Infrastruct. Eng. 2018, 33, 333–350. [CrossRef]
15. Shetty, S.; Shetty, S.; Singh, C.; Rao, A. Supervised machine learning: Algorithms and applications. In Fundamental and Methods of
Machine and Deep Learning: Algorithms, Tools and Applications; Wiley: Hoboken, NJ, USA, 2022; pp. 1–16.
16. Abbasi, H.; Bennet, L.; Guann, J.; Unsworth, C. Latent phase detection of hypoxic-ischemic spike transients in the EEG of preterm
fetal sheep using reverse biorthogonal wavelets and fuzzy classifier. Int. J. Neural Syst. 2019, 29, 195–212. [CrossRef] [PubMed]
17. Quinlan, J. Introduction of decision trees. Mach. Learn. 1986, 1, 81–106. [CrossRef]
18. Lopez-Rubio, E.; Molina-Cabello, E.; Lique-Baena, M.; Dominguez, E. Foreground detection by competitive learning for varying
input distributions. Int. J. Neural Syst. 2018, 28, 175–191. [CrossRef]
19. Chen, Z.; Liu, C. Roadway asset inspection sampling using high-dimensional clustering and locality-sensitivity hashing.
Comput.-Aided Civ. Infrastruct. Eng. 2019, 34, 116–129. [CrossRef]
20. Tramel, W.; Gabrie, M.; Manoel, A.; Caltagirone, F.; Krozakala, F. Deterministic and generalized framework for unsupervised
learning with restricted Boltzmann machines. Phys. Rev. 2018, 8, 041006. [CrossRef]
21. Marugan, A. Applications of reinforcement learning for maintenance of engineering systems:A review. Adv. Eng. Softw. 2023,
183, 103–117. [CrossRef]
22. Park, J.; Park, J. Enhanced machine learning algorithms: Deep learning, reinforcement learning and Q-learning. J. Inf. Process.
Syst. 2020, 16, 1001–1007.
23. Abdi, J.; Moshiri, B. Application of temporal difference learning rules in short-term traffic flow prediction. Expert Syst. 2015,
32, 49–64. [CrossRef]
24. Ahmad, T.; Chen, H. Deep learning for multi-scale smart energy forecasting. Energy 2019, 175, 98–112. [CrossRef]
25. Bishop, C. Pattern Recognition and Machine Learning; Information science and statistics; Springer: New York, NY, USA, 2006.
26. Andrew, G.; Ritchard, B.; Sutton, S. Reinforcement Learning, 2nd ed.; The MIT Press: Cambridge, MA, USA, 2018.
27. Jiang, T.; Gradus, J.L.; Rosellini, A. Supervised machine learning: A brief primer. Behav. Ther. 2020, 51, 675–687. [CrossRef]
[PubMed]
Buildings 2024, 14, 3515 29 of 36

28. Singh, A.; Thakur, N.; Sharma, A. A review of supervised machine learning algorithms. Behav. Ther. 2016, 3, 16–32.
29. Osisanwo, Y.; Akinsola, T.; Awodele, O.; Hinmikaiye, O.; Olakanmi, O.; Akinjobi, J. Supervised machine learning algorithms:
Classification and comparison. Int. J. Comput. Trends Technol. 2017, 48, 128–138.
30. Kotsiantis, B.; Zaharakis, L.; Pintelas, P. Supervised machine learning: A review of classification techniques. Emerg. Artif. Intell.
Appl. Comput. Eng. 2007, 160, 3–24.
31. Belavagi, M.; Muniyal, B. Performance evaluation of supervised machine learning algorithms for the intrusion detection. Procedia
Comput. Sci. 2016, 89, 117–123. [CrossRef]
32. Kim, E.; Kim, W.; Lee, Y. Combination of multiple classifiers for the customers purchase behavior prediction. Decis. Support Syst.
2003, 34, 167–175. [CrossRef]
33. Huang, J.; Li, Y.; Xie, M. An empirical analysis of data preprocessing for machine learning-based software cost estimation. Inf.
Softw. Technol. 2015, 67, 108–127. [CrossRef]
34. Miseta, T.; Fodor, A.; Vathy-Fogarassy, A. Surpassing early stopping:A novel correlation-based stopping criterion for neural
networks. Neurocomputing 2024, 567, 127028. [CrossRef]
35. Ahmed, U.; Momtaz, R.; Anwar, H.; Shan, A.; Ifran, R.; Nieto, J. Efficient water quality prediction using supervised machine
learning. Water 2019, 11, 2210. [CrossRef]
36. Fernandez, A.; Bella, J.; Dorronsoro, J. Supervised outlier detection for classification and regression. Neurocomputing 2022,
486, 77–92. [CrossRef]
37. Praveena, M.; Jaiganesh, V. A literature review on supervised machine learning algorithms and boosting process. Int. J. Comput.
Appl. 2017, 169, 975–988. [CrossRef]
38. Jaccard, J.; Wan, C.; Turrisi, R. The detection and interpretation of interaction effects between continuous variables in multiple
regression. Multivar. Behav. Res. 1990, 25, 467–478. [CrossRef] [PubMed]
39. Bahnsen, A.; Aouacha, D.; Ottersten, B. Dependent cost-sensitive decision trees. Expert Syst. Appl. 2015, 42, 6609–6619. [CrossRef]
40. Maulud, D.; Abdulazez, A. A review on linear regression comprehensive in machine learning. J. Appl. Sci. Technol. Trends 2020,
1, 140–147. [CrossRef]
41. Utkin, V.; Zhuk, Y. A one-class classification support vector machine model by interval-valued training data. Knowl.-Based Syst.
2017, 120, 43–56. [CrossRef]
42. Castillo-Botón, C.; Casillas-Pérez, D.; Casanova-Mateo, C.; Ghimire, S.; Cerro-Prada, E.; Gutierrez, P.; Deo, R.; Salcedo-Sanz, S.
Machine learning regression and classification methods for fog events prediction. Atmos. Res. 2022, 272, 106157. [CrossRef]
43. Wojtowytsch, S. Stochastic gradient descent with noise of machine learning type 1:Discrete time analysis. J. Nonlinear Sci. 2023,
33, 45. [CrossRef]
44. Polyak, B. Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 1964, 4, 1–17.
[CrossRef]
45. Peng, Y.; Lee, W. Practical guidelines for resolving the loss divergence caused by the root-mean-aquared propagation optimizer.
Appl. Soft Comput. 2024, 153, 13–37. [CrossRef]
46. Lioyd, S.; Mohsen, M.; Robentrost, P. Quantum algorithms for supervised and unsupervised machine learning. Int. J. Quantuum
Phys. 2013, 3, 17–32.
47. Hofmann, T. Unsupervised learning by probabilistic latent semantic analysis. Int. J. Mach. Learn. 2001, 42, 177–196. [CrossRef]
48. Sinaga, K.; Yang, M. Unsupervised K-means clustering algorithm. IEEE Access 2020, 8, 80716–80727. [CrossRef]
49. Mathias, S.; Slager, R. Unsupervised machine learning and band topology. Phys. Rev. Lett. 2020, 124, 226–241.
50. Einst, D.; Wehenkel, L.; Geurts, P. Trees-based batch mode reinforcement learning. J. Mach. Learn. Res. 2005, 6, 503–2556.
51. Lin, J. Self improving reactive agents based on reinforcement learning, planning and teaching. J. Mach. Learn. Res. 1992,
8, 293–321. [CrossRef]
52. Riedmiller, M. Concepts and facilities of a neural reinforcement learning control architecture for technical process control. J.
Neural Comput. Appl. 2000, 8, 323–338. [CrossRef]
53. Agarwal, A.; Kakade, S.; Lee, J.; Mahajen, G. On the theory of policy gradient methods: Optimality, approximation and
distribution shift. J. Mach. Learn. Res. 2021, 22, 1–76.
54. Aswani, A.; Gonzalez, H.; Sastry, S.; Tomlin, G. Probably safe and robust learning-based model predictive control. Automatica
2013, 49, 1216–1226. [CrossRef]
55. Azar, M.; Munos, R.; Kappen, H. Minimax bounds on the sample, complexity of reinforcement learning with a generative model.
Mach. Learn. 2013, 91, 325–349. [CrossRef]
56. Sutton, R.; Andrew, B. Reinforcement learning: An introduction. Robotica 1999, 17, 229–235. [CrossRef]
57. Ethem, A. Introduction to Machine Learning; MIT Press: Cambridge, MA, USA, 2020.
58. Ahmed, N.; Atiya, A.; Gayar, N.; El-shishiny, H. An empirical comparison of machine learning models for time series forecasting.
Econ. Rev. 2010, 29, 594–621. [CrossRef]
59. Carbonneau, R.; Lafiamboise, K.; Vaidov, R. Application of machine learning techniques for supply chain demand forecasting.
Eur. J. Oper. Res. 2008, 184, 1140–1154. [CrossRef]
60. Ghaboussi, J.; Garrett, J.; Xiping, W. Knowledge-based modeling of material behavior with neural networks. J. Eng. Mech. 1991,
117, 132–153. [CrossRef]
61. Yeh, I.C. Modeling concrete strength with augment-neuron networks. J. Mater. Civ. Eng. 1998, 10, 263–268. [CrossRef]
Buildings 2024, 14, 3515 30 of 36

62. Janusz, K.; Janusz, R.; Artur, D. HPC strength prediction using artificial neural network. J. Comput. Civ. Eng. 1995, 9, 279–284.
63. Yeh, I.C. Design of high-performance concrete mixture using neural networks and nonlinear programming. J. Comput. Civ. Eng.
1999, 13, 36–42. [CrossRef]
64. Trent, S.; Renno, J.; Sassi, S.; Mohamed, S. Using image processing techniques in computational mechanics. Comput. Math. Appl.
2023, 136, 1–24. [CrossRef]
65. Capuano, G.; Rimoli, J. J. Smart finite elements: A novel machine learning. Comput. Methods Appl. Mech. Eng. 2019, 345, 363–381.
[CrossRef]
66. Nashed, M.; Renno, J.; Mohamed, S. Nonlinear analysis of shell structures using image processing and machine learning. Adv.
Eng. Softw. 2023, 176, 103392. [CrossRef]
67. Cabrera, M.; Ninic, J.; Tizani, W. Fusion of experimental and synthetic data for reliable prediction of steel connection behaviour
using machine learning. Eng. Comput. 2023, 39, 3993–4011. [CrossRef]
68. Bolaji, O.; Helio, M.; Krishnan, A.; Sumanta, D. Integrating Experiments, Finite Element Analysis, and Interpretable Machine
Learning to Evaluate the Auxetic Response of 3D Printed Re-entrant Metamaterials. J. Mater. Res. Technol. 2023, 25, 1612–1625.
69. Liang, L.; Liu, M.; Martin, C.; Sun, W. A deep learning approach to estimate stress distribution: A fast and accurate surrogate of
finite-element analysis. J. R. Soc. Interface 2018, 15, 20170844. [CrossRef] [PubMed]
70. Silva, G.; Beber, V.; Pitz, D. Machine learning and finite element analysis: An integrated approach for fatigue lifetime prediction
of adhesively bonded joints. Fatigue Fract. Eng. Mater. Struct. 2021, 44, 3334–3348. [CrossRef]
71. Jokar, M.; Semperlotti, F. Finite element network analysis: A machine learning based computational framework for the simulation
of physical systems. Comput. Struct. 2021, 247, 106484. [CrossRef]
72. Koutsourelakis, S. Stochastic upscaling in soild mechanics: An exercise in machine learning. J. Comput. Phys. 2007, 226, 301–325.
[CrossRef]
73. Oishi, A.; Yagawa, G. Computational mechanics enhanced by deep learning. Comput. Methods Appl. Mech. Eng. 2017, 327, 327–351.
[CrossRef]
74. Kirchdoerfer, T.; Ortiz, M. Data-driven computational mechanics. Comput. Methods Appl. Mech. Eng. 2016, 304, 81–101. [CrossRef]
75. Lees, H.; Kang, S. Neural algorithm for solving differential equations. J. Comput. Phys. 1990, 91, 110–131.
76. Meade, J.; Fernandez, A. The numerical solution of linear ordinary differential equations by feedward neural networks. Math.
Comput. Model. 1994, 91, 1–25. [CrossRef]
77. Lagaris, E.; Likas, A.; Fotiadis, I. Artificial neural networks for solving ordinary and partial differential equations. Trans. Neural
Netw. 1998, 9, 987–1000. [CrossRef] [PubMed]
78. Wu, L.; Wang, X.; Xiao, H.; Ling, J. A priori assessment of prediction confidence for data-driven turbulance modeling. Flow
Turbul. Combust. 2017, 99, 25–46. [CrossRef]
79. Xiao, H.; Wu, L.; Wang, H.; Sun, R.; Roy, J. Quantifying and reducing model-form uncertainties in Reynolds averaged Navier-
stokes simulations. J. Comput. Phys. 2016, 324, 115–136. [CrossRef]
80. Weinan, E.; Han, J.; Jentzen, A. Deep learning-based numerical methods for high-dimensional parabolic partial differential
equations and backward stochastic differential equations. Commun. Math. Stat. 2017, 5, 349–380.
81. Berg, J.; Nystorm, K. A unified deep artificial neural network approach to partial differential equations in complex geometries.
Neurocomputing 2018, 317, 28–41. [CrossRef]
82. Trask, N.; Patel, R.; Paul, B.; Atzberger, J. GMLS-Nets: Aframe work for learning from unstructured data. Comput. Sci. 2019,
7, 15–29.
83. Dufera, T. Deep neural network for system of ordinary differential equatuions: Vectorized algorithm and simulation. Mach.
Learn. Appl. 2021, 5, 532–549.
84. Guo, Y.; Cao, X.; Liu, B.; Gao, M. Solving partial differential equations using deep learning and physical constraints. Appl. Sci.
2020, 10, 5917. [CrossRef]
85. Saha, S.; Gan, Z.; Cheng, L.; Gao, J.; Kafka, O.; Xie, X.; Li, H.; Tajdari, M.; Kim, H.; Liu, W. Hierarchical deep learning neural
network HiDeNN: An artificial intelligence AI framework for computational science and engineering. Comput. Methods Appl.
Mech. Eng. 2021, 378, 113452. [CrossRef]
86. Raissi, M.; Perdikaris, P.; Karniadakis, E. Physics-informed neural networks:Adeep learning framework for solving forward and
inverse problems involving nonlinear partial differential equations. J. Comput. Phys. 2019, 378, 686–707. [CrossRef]
87. Raissi, M.; Karniadakis, E. Machine learning of nonlinear partial differential equations. J. Comput. Phys. 2018, 357, 125–141.
[CrossRef]
88. Badarinath, V.; Chierichetti, M.; Kakhki, F. A machine learning approach as a surrogate for a finite element analysis: Status of
research and application to one dimensional systems. Sensors 2021, 21, 1654. [CrossRef] [PubMed]
89. Hashemi, A.; Jang, J.; Beheshti, J. A Machine Learning-Based Surrogate Finite Element Model for Estimating Dynamic Response
of Mechanical Systems. IEEE Access 2023, 11, 54509–54525. [CrossRef]
90. Lu, M.; Mohammadi, A.; Meng, Z.; Meng, X.; Li, G.; Li, Z. Deep neural operator for learning transient response of interpenetrating
phase composites subject to dynamic loading. Comput. Mech. 2023, 72, 563–576. [CrossRef]
91. Li, Q.; Wang, Z.; Li, L.; Hao, H.; Chen, W.; Shao, Y. Machine learning prediction of structural dynamic responses using graph
neural networks. Comput. Struct. 2023, 289, 107188. [CrossRef]
Buildings 2024, 14, 3515 31 of 36

92. Najera-Flores, D.A.; Quinn, D.D.; Garland, A.; Vlachas, K.; Chatzi, E.; Todd, M.D. A structure-preserving machine learning
framework for accurate prediction of structural dynamics for systems with isolated nonlinearities. Mech. Syst. Signal Process.
2024, 213, 111340. [CrossRef]
93. Jung, J.; Jun, H.; Lee, P. Self-updated four-node finite element using deep learning. Comput. Mech. 2022, 69, 23–44. [CrossRef]
94. Logarzo, H. J.; Capuano, G.; Rimoli, J. J. Smart constitutive laws: Inelastic homogenization through machine learning. Comput.
Methods Appl. Mech. Eng. 2021, 373, 113482. [CrossRef]
95. Brevis, I.; Muga, I.; der Zee, K.V. A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element
discretizations. Comput. Math. Appl. 2021, 95, 186–199. [CrossRef]
96. Mishra, S. A machine learning framework for data driven acceleration of computations of differential equations. Math. Eng. 2018,
1, 118–146. [CrossRef]
97. Farrarand, C.; Worden, K. An introduction to structural health monitoring. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2007,
365, 303–315. [CrossRef] [PubMed]
98. De Iuliis, M.; Miceli, E.; Castaldo, P. Machine learning modelling of structural response for different seismic signal characteristics:
A parametric analysis. Appl. Soft Comput. 2024, 164, 112026. [CrossRef]
99. Brownjohn, J. Structural health monitoring of civil infrastructure. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 2007, 365, 589–622.
[CrossRef] [PubMed]
100. Wagg, J.; Worden, K.; Barthorpe, R.; Gardner, P. Digital twins: State-of-the-art and future directions for modeling and simulation
in engineering dynamics applications. ASCE-ASME J. Risk Uncertain. Eng. Syst. Part B Mech. Eng. 2020, 6, 030901. [CrossRef]
101. Tronci, E.; Beigi, H.; Feng, M.; Betti, R. A transfer learning SHM strategy for bridges enriched by the use of speaker recognition
x-vectors. J. Civ. Struct. Health Monit. 2022, 12, 1285–1298. [CrossRef]
102. Worden, K.; Manson, G. The application of machine learning to structural health monitoring. Philos. Trans. R. Soc. A Math. Phys.
Eng. Sci. 2007, 365, 515–537. [CrossRef]
103. Farrar, C.; Doebling, S.; Nix, D. Vibration–based structural damage identification. Philos. Trans. R. Soc. Lond. Ser. A Math. Phys.
Eng. Sci. 2001, 359, 131–149. [CrossRef]
104. Yeh, I.C.; Yau-Hwaug, K.; Deh-Shiu, H. Building KBES for diagnosing PC pile with artificial neural network. J. Comput. Civ. Eng.
1993, 7, 71–93. [CrossRef]
105. González, P.; Zapico, L. Seismic damage identification in buildings using neural networks and modal data. Comput. Struct. 2008,
86, 416–426. [CrossRef]
106. Chang, C.; Lin, T.; Chang, C. Applications of neural network models for structural health monitoring based on derived modal
properties. Measurement 2018, 129, 457–470. [CrossRef]
107. Soyoz, S.; Feng, Q. Long-term monitoring and identification of bridge structural parameters. Comput.-Aided Civ. Infrastruct. Eng.
2009, 24, 82–92. [CrossRef]
108. Peng, J.; Zhang, S.; Peng, D.; Liang, K. Application of machine learning method in bridge health monitoring. In Proceedings
of the 2017 Second International Conference on Reliability Systems Engineering (ICRSE), Beijing, China, 10–12 July 2017; IEEE:
Piscataway, NJ, USA, 2017; pp. 1–7.
109. Giglioni, V.; Venanzi, I.; Ubertini, F. Supervised machine learning techniques for predicting multiple damage classes in bridges.
In Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, Long Beach, CA, USA, 12–17
March 2023; Volume 12486, p. 1248617.
110. Kao, C.; Loh, C. Monitoring of long-term static deformation data of Fei-Tsui arch dam using artificial neural network-based
approaches. Struct. Control Health Monit. 2013, 20, 282–303. [CrossRef]
111. Ranković, V.; Grujović, N.; Divac, D.; Milivojević, N. Development of support vector regression identification model for prediction
of dam structural behaviour. Struct. Saf. 2014, 48, 33–39. [CrossRef]
112. Santillán, D.; Fraile-Ardanuy, J.; Toledo, M.Á. Prediction of gauge readings of filtration in arch dams using artificial neural
networks. Tecnol. Cienc. Agua 2014, 5, 81–96.
113. Song, J.; Yuan, S.; Xu, Z.; Li, X. Fast inversion method for seepage parameters of core earth-rock dam based on LHS-SSA-MKELM
fusion surrogate model. Structures 2023, 55, 160–168. [CrossRef]
114. Taylor, M.; Stone, P. Transfer learning for reinforcement learning domains: A survey. J. Mach. Learn. Res. 2009, 10, 1633–1685.
115. Zhuang, F.; Qi, Z.; Duan, K.; Xi, D.; Zhu, Y.; Zhu, H.; Xiong, H.; He, Q. A Comprehensive survey on transfer learning. Proc. IEEE
2021, 109, 43–76. [CrossRef]
116. Gardner, P.; Bull, L.; Dervilis, N.; Worden, K. On the application of Kernelised Bayesian transfer learning to population-based
structural health monitoring. Mech. Syst. Signal Process. 2022, 167, 108519. [CrossRef]
117. Gosliga, J.; Hester, D.; Worden, K.; Bunce, A. On Population-based structural health monitoring for bridges. Mech. Syst. Signal
Process. 2022, 173, 108919. [CrossRef]
118. Bao, N.; Zhang, T.; Huang, R.; Biswal, S.; Su, J.; Wang, Y. A deep transfer learning network for structural condition identification
with limited real-world training data. Struct. Control Health Monit. 2023, 8899806. [CrossRef]
119. Li, Y.; Bao, T.; Gao, Z.; Shu, X.; Zhang, K.; Xie, L.; Zhang, Z. A new dam structural response estimation paradigm powered by
deep learning and transfer learning techniques. Struct. Health Monit. 2022, 21, 770–787. [CrossRef]
Buildings 2024, 14, 3515 32 of 36

120. Tsialiamanis, G.; Wagg, D.; Gardner, P.; Dervilis, N.; Worden, K. On partitioning of an SHM problem and parallels with transfer
learning. In Topics in Modal Analysis & Testing, Volume 8: Proceedings of the 38th IMAC, A Conference and Exposition on Structural
Dynamics 2020; Springer: Cham, Switzerland, 2021; pp. 41–50.
121. Azad, M.; Kim, S.; Cheon, Y.; Kim, H. Intelligent structural health monitoring of composite structures using machine learning,
deep learning, and transfer learning: A review. Adv. Compos. Mater. 2023, 33, 162–188. [CrossRef]
122. Kamariotis, A.; Chatzi, E.; Straub, D. A framework for quantifying the value of vibration-based structural health monitoring.
Mech. Syst. Signal Process. 2023, 184, 109708. [CrossRef]
123. Markogiannaki, O.; Arailopoulos, A.; Giagopoulos, D.; Papadimitriou, C. Vibration-based Damage Localization and Quantifica-
tion Framework of Large-Scale Truss Structures. Struct. Health Monit. 2023, 22, 1376–1398. [CrossRef]
124. Pizarro, P.; Massone, L. Structural design of reinforced concrete buildings based on deep neural networks. Eng. Struct. 2021,
241, 112377. [CrossRef]
125. Chaillou, S. Archigan: Artificial intelligence x architecture. In Architectural Intelligence: Selected Papers from the 1st International
Conference on Computational Design and Robotic Fabrication (CDRF 2019); Springer: Berlin/Heidelberg, Germany, 2020; pp. 117–127.
126. Ampanavos, S.; Nourbakhsh, M.; Cheng, C. Structural design recommendations in the early design phase using machine learning.
In International Conference on Computer-Aided Architectural Design Futures; Springer: Singapore, 2022; pp. 190–202.
127. Rasoulzadeh, S.; Senk, V.; Königsberger, M.; Reisinger, J.; Kovacic, I.; Füssl, J.; Wimmer, M. A novel integrative design framework
combining 4D sketching, geometry reconstruction, micromechanics material modelling, and structural analysis. Adv. Eng.
Informatics 2023, 57, 102074. [CrossRef]
128. Liao, W.; Lu, X.; Huang, Y.; Zheng, Z.; Lin, Y. Automated structural design of shear wall residential buildings using generative
adversarial networks. Autom. Constr. 2021, 132, 103931. [CrossRef]
129. Zhang, Y.; Mueller, C. Shear wall layout optimization for conceptual design of tall buildings. Eng. Struct. 2017, 140, 225–240.
[CrossRef]
130. Lou, H.; Gao, B.; Jin, F.; Wan, Y.; Wang, Y. Shear wall layout optimization strategy for high-rise buildings based on conceptual
design and data-driven tabu search. Comput. Struct. 2021, 250, 106546. [CrossRef]
131. Chang, K.; Cheng, C. Learning to simulate and design for structural engineering. In Proceedings of the International Conference
on Machine Learning, PMLR, Virtual, 13–18 July 2020; pp. 1426–1436.
132. Preisinger, C.; Heimrath, M. Karamba—A toolkit for parametric structural design. Struct. Eng. Int. 2014, 24, 217–221. [CrossRef]
133. Khayam, S.; Ajmal, A.; Park, J.; Kim, I.; Park, J. Tendon Stress Estimation from Strain Data of a Bridge Girder Using Machine
Learning-Based Surrogate Model. Sensors 2023, 23, 5040. [CrossRef] [PubMed]
134. Motsa, S.M.; Stavroulakis, G.E.; Drosopoulos, G.A. A data-driven, machine learning scheme used to predict the structural
response of masonry arches. Eng. Struct. 2023, 296, 116912. [CrossRef]
135. Habib, M.; Bashir, B.; Alsalman, A.; Bachir, H. Evaluating the accuracy and effectiveness of machine learning methods for rapidly
determining the safety factor of road embankments. Multidiscip. Model. Mater. Struct. 2023, 19, 966–983. [CrossRef]
136. Skordaris, G.; Bouzakis, K.; Charalampous, P.; Kotsanis, T.; Bouzakis, E.; Bejjani, R. Bias voltage effect on the mechanical
properties, adhesion and milling performance of PVD films on cemented carbide inserts. Wear 2018, 404, 50–61. [CrossRef]
137. Fu, Z.; Yang, W.; Wang, X.; Leopold, J. An analytical force model for ball-end milling based on a predictive machine theory
considering cutter runout. Int. J. Adv. Manuf. Technol. 2017, 93, 2061–2069.
138. Newby, G.; Venkatachalam, S.; Liang, S. Empirical analysis of cutting force constants in Micro-end-milling operations. J. Mater.
Process. Technol. 2007, 192, 41–47. [CrossRef]
139. Man, X.; Ren, D.; Usui, C.; Johnson, T.; Marusich, T. Validation of finite element cutting force prediction for end milling. Procedia
CIRP 2012, 1, 663–668. [CrossRef]
140. Michailidis, N.; Kombogiannis, S.; Charalampous, P.; Maliaris, G.; Stegioudi, F. Computational-experimental investigations of
milling porous Aluminimum. CIRP Ann. 2017, 66, 121–124. [CrossRef]
141. Charalampous, P. Prediction of cutting forces in milling using machine learning algorithms and finite element analysis. J. Mater.
Eng. Perform. 2002, 30, 2002–2012. [CrossRef]
142. Jirousek, O.; Palar, P.; Falta, J.; Dwianto, Y. Design exploration of additively manufactured chiral auxetic structure using
explainable machine learning. Mater. Des. 2023, 232, 112128.
143. Grozav, S.; Sterca, A.; Kočiško, M.; Pollák, M.; Ceclan, V. Artificial Neural Network-Based Predictive Model for Finite Element
Analysis of Additive-Manufactured Components. Machines 2023, 11, 547. [CrossRef]
144. Dwyer, A.; Mathews, B.; Azadani, A.; Ge, L.; Guy, S.; Tseng, E. Migration forces of transcatheter aortic valves in patients with
noncalcific aortic insufficiency. J. Thorac. Cardiovasc. Surg. 2009, 138, 1227–1233. [CrossRef] [PubMed]
145. Aurccio, F.; Conti, M.; Morganti, S.; Reali, A. Simulations of transcather aortic valve implementation: Apatient-specific finite
element approach. Comput. Methods Biomech. Biomed. Eng. 2014, 17, 1347–1357. [CrossRef] [PubMed]
146. Liang, L.; Minliang, L.; John, E.; Wei, S. Synergistic integration of deep neural networks and finite element method with
applications of nonlinear large deformation biomechanics. Comput. Methods Appl. Mech. Eng. 2023, 416, 116–218. [CrossRef]
147. Jiang, H.; Nie, Z.; Yeo, R.; Farimani, A.; Burak, K. Stressgan: A generative deep learning model for two-dimensional stress
distribution prediction. J. Appl. Mech. 2021, 88, 051005. [CrossRef]
148. Kazeruni, M.; Ince, A. Data-driven artificial neural network for elastic plastic stress and strain computation for notched bodies.
Theor. Appl. Fract. Mech. 2023, 125, 103917. [CrossRef]
Buildings 2024, 14, 3515 33 of 36

149. Yan, W.; Deng, L.; Zhang, F.; Li, T.; Li, S. Probabilistic machine learning approach to bridge fatigue failure analysis due to
vehicular overloading. Eng. Struct. 2019, 193, 91–99. [CrossRef]
150. Reiner, J.; Linden, N.; Vaziri, R.; Zobeiry, N.; Kramer, B. Bayesian parameter estimation for the inclusion of uncertainty in
progressive damage simulation of composites. Compos. Struct. 2023, 321, 117257. [CrossRef]
151. Bui, Q.; Tran, V.; Shan, A. Improved knowledge-based neural network (KBNN) model for predicting spring-back angles in metal
sheet bending. Int. J. Model. Simul. Sci. Comput. 2014, 5, 135–146. [CrossRef]
152. Rafiq, Y.; Bugmann, G.; Easterbrook, J. Neural network design for engineering applications. Comuters Struct. 2001, 79, 1541–1552.
[CrossRef]
153. Kan, S.; Tan, C.; Mathew, J. A review on prognostic techniques for non-stationary and non-linear totating systems. Mech. Syst.
Signal Process. 2015, 62, 1–20. [CrossRef]
154. Yu, S.; Qi, S.; Liu, L.; Xu, Q.; Wu, L.; Zeng, W. Application of the Ultrasonic Guided Wave Technique Based on PSO-ELM
Algorithm in the Rail Fatigue Crack Assessment. J. Test. Eval. 2023, 51, JTE20220569. [CrossRef]
155. Cheng, Y.; Huang, L.; Zhou, Y. Artificial neural network technology for the data processing of one-line corrosion fatigue crack
growth monitoing. Int. J. Pres. Ves. Pip 1999, 76, 113–116. [CrossRef]
156. Zio, E.; Maio, D. Fatigue crack growth estimation by relevance vector machine. Expert Syst. Appl. 2012, 39, 10681–10692.
[CrossRef]
157. Mohanty, R.; Mahanta, K.; Mohanty, A.; Thatoi, N. Prediction of constant amplitude fatigue crack growth life of 2024T3 AI alloy
with R-ratio effect by GP. Appl. Soft Comput. 2014, 26, 428–434. [CrossRef]
158. Tan, H.; Bi, H.; Hou, L.; Wong, W. Reliability analysis using radial basis function networks and support vector machines. Comput.
Geotech. 2011, 38, 178–186. [CrossRef]
159. Heng, Y. Intelligent prognostics of machinery health utilising suspended condition monitoring data. Comput. Geotech. 2011,
38, 178–186.
160. Hashash, Y.; Jung, S.; Ghaboussi, J. Numerical implementation of a neural network based material model in finite element
analysis. Int. J. Numer. Methods Eng. 2004, 59, 989–1005. [CrossRef]
161. Carneiro, A.; Alves, A.; Coelho, R.; Cardoso, J.; Pires, F. A simple machine learning-based framework for faster multi-scale
simulations of path-independent materials at large strains. Finite Elem. Anal. Des. 2023, 222, 103956. [CrossRef]
162. Nikolić, F.; Čanad̄ija, M. Deep Learning of Temperature–Dependent Stress–Strain Hardening Curves. C. R. Mécanique 2023,
351, 151–170. [CrossRef]
163. Fazily, P.; Yoon, J. Machine learning-driven stress integration method for anisotropic plasticity in sheet metal forming. Int. J. Plast.
2023, 166, 103642. [CrossRef]
164. Long, C.; Liu, S.; Sun, R.; Lu, J. Impact of structural characteristics on thermal conductivity of foam structures revealed with
machine learning. Comput. Mater. Sci. 2024, 237, 112898. [CrossRef]
165. Gang, M.; Shaoheng, G.; Qiao, W.; YT, F.; Wei, Z. A predictive deep learning framework for path-dependent mechanical behavior
of granular materials. Acta Geotech. 2022, 17, 3463–3478.
166. Mital, U.; José, A. Bridging length scales in granular materials using convolutional neural networks. Comput. Part. Mech. 2022,
9, 221–235. [CrossRef]
167. Guan, S.; Qu, T.; Feng, Y.T.; Ma, G.; Zhou, W. A machine learning-based multi-scale computational framework for granular
materials. Acta Geotech. 2022, 18, 1699–1720. [CrossRef]
168. Hakim, S.; Noorzaei, J.; Jaafar, M.; Jameel, M.; Mohammadhassani, M. Application of artificial neural networks to predict
compressive strength of high strength concrete. Int. J. Phys. Sci. 2011, 6, 975–981.
169. Al-Janabi, K.; Abdulwahab, A. Modeling of polymer modified-concrete strength with artificial neural networks. Int. J. Civ. Eng.
2008, 10, 47–68.
170. Kim, J.; Kim, D.; Feng, M.; Yazdani, F. Application of neural networks for estimation of concrete strength. J. Mater. Civ. Eng. 2004,
16, 257–264. [CrossRef]
171. Kim, K.; Lee, J.; Chang, K. Application of probabilistic neural networks for prediction of concrete strength. J. Mater. Civ. Eng.
2005, 17, 353–362. [CrossRef]
172. Gupta, R.; kewalramani, A.; Geol, A. Prediction of concrete strength using neural-expert system. J. Mater. Civ. Eng. 2006,
18, 462–466. [CrossRef]
173. Roberson, M.; Inman, K.; Carey, A.; Howard, I.; Shannon, J. Probabilistic neural networks that predict compressive strength of
high strength concrete in mass placements using thermal history. Comput. Struct. 2022, 259, 106707. [CrossRef]
174. Yang, Y.; Zhang, J.; Huang, F.; Chen, Z.; Qiu, R.; Wu, S. Effect of structural parameters on compression performance of autoclaved
aerated concrete: Simulation and machine learning. Constr. Build. Mater. 2024, 423, 135860. [CrossRef]
175. Korza, R. Genetic Programming: On the Programming of Computers by Natural Selection; MIT Press: Cambridge, MA, USA, 2018;
Volume 339, pp. 358–388.
176. Hein, D.; Udluft, S.; Runkler, A. Interpretable policies for reinforcement learning by genetic programming. Eng. Appl. Artif. Intell.
2018, 76, 158–167. [CrossRef]
177. Nicholas, A.; Kamran, B.; Zouheir, F. Applicability and viability of a GA based finite element analysis architecture for structural
design optimization. Comput. Struct. 2003, 81, 2259–2271.
Buildings 2024, 14, 3515 34 of 36

178. Hashem, B.; Zahidul, I. Advantages and limitations of genetic algorithms for clustering records. In Proceedings of the 2016 IEEE
11th Conference on Industrial Electronics and Applications (ICIEA), Hefei, China, 5–7 June 2016; IEEE: Piscataway, NJ, USA, 2016;
pp. 2478–2483.
179. Guan, X.; Burton, H. Bias-variance tradeoff in machine learning: Theoretical formulation and implications to structural
engineering applications. Structures 2022, 46, 17–30. [CrossRef]
180. Gharahamani, Z. Unsupervised learning. Adv. Lect. Mach. Learn. 2004, 16, 362–379.
181. Benyamin, G.; Crowley, M.; Karray, F.; Ghodsi, A. Locally linear embedding. In Elements of Dimensionality Reduction and Manifold
Learning; Springer International Publishing: Cham, Switzerland, 2023; Volume 404, pp. 207–247.
182. Andrew, M.; Kamal, N.; Jason, R.; Kristie, S. A machine learning approach to building domain-specific search engines. In
Proceedings of the IJCAI, Stockholm, Sweden, 31 July–6 August 1999; Volume 99, pp. 662–667.
183. Magidson, J.; Vermunt, J. Latent class models for clustering: A comparison with K-means. Int. Can. J. Mark. Res. 2002, 20, 13–27.
184. Alcala-Fdez, J.; Sanchez, L.; Garcia, S.; Del-Jesus, M. Software to assess evolutionary algorithms for data mining problems. Soft
Comput. 2008, 6, 93–103.
185. Macqueen, J. Some methods for classification and analysis of multivariate observations. In Proceedings of 5-th Berkeley Symposium
on Mathematical Statistics and Probability; University of California Press: Berkeley, CA, USA, 1967; Volume 1, pp. 281–297.
186. John, H.; Langley, P. Estimating continious distributions in Bayesian classifiers. In Proceedings of the 11th Conference on
Uncertainty in Artificial Intelligence, Montreal, QC, Canada, 18–20 August 1995; Volume 1, pp. 338–345.
187. Rakthanmanon, T.; Keogh, J.; Evans, S. MDL-based time series clustering. Knowl. Inf. Syst. 2012, 33, 371–399. [CrossRef]
188. Saul, L.; Roweis, S. Unsupervised learning of two dimensional manifolds. J. Mach. Learn. Res. 2003, 4, 119–155.
189. Dy, J.; Brodley, C. Feature selection for unsupervised learning. J. Mach. Learn. Res. 2004, 5, 845–889.
190. Bo, L.; Ren, X.; Fox, D. Unsupervised feature learning for RGB-D based object recognition. In Proceedings of the Experimental
Robotics: The 13th International Symposium on Experimental Robotics, Québec City, QC, Canada, 18–21 June 2012; Springer:
Berlin/Heidelberg, Germany, 2013; pp. 387–402.
191. Madan, A. Vibration control of building structures using self-organizing and self-learning neural networks. J. Sounds Vib. 2005,
287, 759–784. [CrossRef]
192. Daneshvar, M.; Hassan, S. Unsupervised learning-based damage assessment of full-scale civil structures under long-term and
short-term monitoring. Eng. Struct. 2022, 256, 114059. [CrossRef]
193. García-Macías, E.; Ubertini, F. Integrated SHM systems: Damage detection through unsupervised learning and data fusion. In
Structural Health Monitoring Based on Data Science Techniques; Springer: Berlin/Heidelberg, Germany, 2021; pp. 247–268.
194. Ma, X.; Lin, Y.; Nie, Z.; Ma, H. Structural damage identification based on unsupervised feature-extraction via Variational
Auto-encoder. Measurement 2020, 160, 107811. [CrossRef]
195. Alireza, E.; Hashem, S. An unsupervised learning approach by novel damage indices in structural health monitoring for damage
localization and quantification. Struct. Health Monit. 2018, 17, 325–345.
196. Alireza, E.; Hashem, S.; Stefano, M. Fast unsupervised learning methods for structural health monitoring with large vibration
data from dense sensor networks. Struct. Health Monit. 2020, 19, 1685–1710.
197. Liu, J.; Li, Q.; Li, L.; An, S. Structural damage detection and localization via an unsupervised anomaly detection method. Reliab.
Eng. Syst. Saf. 2024, 252, 110465. [CrossRef]
198. Junges, R.; Rastin, Z.; Lomazzi, L.; Giglio, M.; Cadini, F. Convolutional autoencoders and CGANs for unsupervised structural
damage localization. Mech. Syst. Signal Process. 2024, 220, 111645. [CrossRef]
199. Eloi, F.; Yano, O.; Samuel, D.; Ionut, M.; Mihai, A. Transfer learning to enhance the damage detection performance in bridges
when using numerical models. J. Bridge Eng. 2023, 28, 04022134.
200. Bayane, I.; Leander, J.; Karoumi, R. An unsupervised machine learning approach for real-time damage detection in bridges. Eng.
Struct. 2024, 308, 117971. [CrossRef]
201. Lu, Y.; Tang, L.; Liu, Z.; Zhou, L.; Yang, B.; Jiang, Z.; Liu, Y. Unsupervised quantitative structural damage identification method
based on BiLSTM networks and probability distribution model. J. Sound Vib. 2024, 590, 118597. [CrossRef]
202. Lieber, D.; Stople, M.; Konrad, B.; Deuse, J.; Morik, K. Quality predictions in interlinked manufacturing processes based on
supervised and unsupervised machine learning. Procedia CIRP 2013, 7, 193–198. [CrossRef]
203. Alwood, M.; Cullen, M. Sustainable Materials; UIT Cambridge Ltd.: Cambridge, UK, 2012; Volume 2, pp. 51–54.
204. Konrad, B.; Lieber, D.; Deuse, J. Striving for zero defect production: Intelligent manufacturing control through data mining in
continious rolling mill processes. Robust Manuf. Control 2012, 1, 67–75.
205. Stolpr, M.; Morik, K. Learning from label proportion by optimizing cluster model selection. Mach. Learn. Knowl. Discov. Databases
2011, 6913, 349–364.
206. Choi, J.; Kim, N.; Hong, Y. Unsupervised Legendre–Galerkin Neural Network for Solving Partial Differential Equations. IEEE
Access 2023, 11, 23433–23446. [CrossRef]
207. Zhu, Y.; Nicholas, Z.; Phaedon-Stelios, K.; Paris, P. Physics-constrained deep learning for high-dimensional surrogate modeling
and uncertainty quantification without labeled data. J. Comput. Phys. 2019, 394, 56–81. [CrossRef]
208. Piervincenzo, R.; Marcello, C.; Debaditya, D.; Hoon, S.; Kent, H. An unsupervised learning algorithm for fatigue crack detection
in waveguides. Smart Mater. Struct. 2009, 18, 025016.
Buildings 2024, 14, 3515 35 of 36

209. Hau, M.; Qui, L.; Kang, J.; Lee, J. A novel deep unsupervised learning-based framework for optimization of truss structures. Eng.
Comput. 2022, 39, 2585–2608.
210. Pan, J.; Huang, J.; Wang, Y.; Cheng, G.; Zeng, Y. A self-learning finite element extraction system based on reinforcement learning.
AI EDAM 2021, 35, 180–208. [CrossRef]
211. Soheila, E.; Soheil, E.; Debarshi, S.; Shamim, P. Active structural control framework using policy-gradient reinforcement learning.
Eng. Struct. 2023, 274, 115122.
212. Wei, S.; Bao, Y.; Li, H. Optimal policy for structure maintenance: A deep reinforcement learning framework. Struct. Saf. 2020,
83, 101906. [CrossRef]
213. Yu, C.-H.; Tseng, B.-Y.; Yang, Z.; Tung, C.-C.; Zhao, E.; Ren, Z.-F.; Yu, S.-S.; Chen, P.-Y.; Chen, C.-S.; Buehler, M.J. Hierarchical
Multiresolution Design of Bioinspired Structural Composites Using Progressive Reinforcement Learning. Adv. Theory Simul.
2022, 5, 2200459. [CrossRef]
214. Dhaya, R.; Kanthavel, R.; Fahad, A.; Jayarajan, P.; Mahor, A. Reinforcement learning concepts ministering smart city applications
using IoT. In Internet of Things in Smart Technologies for Sustainable Urban Development; Springer: Cham, Switzerland, 2020;
pp. 19–41.
215. Savinay, N.; Nikhil, P.; Rashmi, U.; Koshy, G. Comparison of reinforcement learning algorithms applied to the cart-pole problem.
In Proceedings of the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI),
Udupi, India, 13–16 September 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 26–32.
216. Bernard, A.; Ian, S. Reinforcement learning for structural control. J. Comput. Civ. Eng. 2008, 22, 133–139.
217. Arash, K.; Mehdi, S.; Masoud, K. Online control of an active seismic system via reinforcement learning. Struct. Control Health
Monit. 2019, 26, e2298.
218. Kazem, S.; Javad, M. Application of reinforcement learning algorithm for automation of canal structures. Irrig. Drain. 2015,
64, 77–84.
219. Dominik, P.; Łukasz, J. Reinforcement learning-based control to suppress the transient vibration of semi-active structures
subjected to unknown harmonic excitation. Comput.-Aided Civ. Infrastruct. Eng. 2022, 38, 1605–1621.
220. Qiu, Z.-C.; Chen, G.-H.; Zhang, X.-M. Reinforcement learning vibration control for a flexible hinged plate. Aerosp. Sci. Technol.
2021, 118, 107056. [CrossRef]
221. Yi, L.; Deng, X.; Yang, L.T.; Wu, H.; Wang, M.; Situ, Y. Reinforcement-learning-enabled partial confident information coverage for
IoT-based bridge structural health monitoring. IEEE Internet Things J. 2020, 8, 3108–3119. [CrossRef]
222. Yang, A.; Qiu, Q.; Zhu, M.; Cui, L.; Chen, W.; Chen, J. Condition-based maintenance strategy for redundant systems with arbitrary
structures using improved reinforcement learning. Reliab. Eng. Syst. Saf. 2022, 225, 108643. [CrossRef]
223. Cao, P.; Tang, J. A Reinforcement Learning Hyper-Heuristic in Multi-Objective Single Point Search with Application to Structural
Fault Identification. arXiv 2018, arXiv:1812.07958.
224. Cao, P.; Zhang, Y.; Zhou, K.; Tang, J. A reinforcement learning hyper-heuristic in multi-objective optimization with application to
structural damage identification. Struct. Multidiscip. Optim. 2023, 66, 16. [CrossRef]
225. Zimmerling, C.; Poppe, C.; Stein, O.; Kärger, L. Optimisation of manufacturing process parameters for variable component
geometries using reinforcement learning. Mater. Des. 2022, 214, 110423. [CrossRef]
226. Harley, O.; Ying, L.; Maneesh, K.; Michael, W.; Michael, R. Reinforcement learning for facilitating human–robot-interaction in
manufacturing. J. Manuf. Syst. 2020, 56, 326–340.
227. Jonathan, V.; Jean, R.; Alexander, K.; Hassan, G.; Aurélien, L.; Elie, H. Direct shape optimization through deep reinforcement
learning. J. Comput. Phys. 2021, 428, 110080.
228. Shaopeng, L.; Reda, S.; Teng, W. A knowledge-enhanced deep reinforcement learning-based shape optimizer for aerodynamic
mitigation of wind-sensitive structures. Comput.-Aided Civ. Infrastruct. Eng. 2021, 36, 733–746.
229. Sérgio, D.; Sidney, G.; Cairo, N. Autonomous construction of structures in a dynamic environment using reinforcement learning.
In Proceedings of the 2013 IEEE International Systems Conference (SysCon), Orlando, FL, USA, 15–18 April 2013; IEEE: Piscataway,
NJ, USA, 2013; pp. 452–459.
230. Kevin, D.; Oliveira, I.; Daniel, D.; Alexandre, G.; Mário, S.; Alexandre, B. Q-learning based Path Planning Method for UAVs
using Priority Shifting. In Proceedings of the 2022 International Conference on Unmanned Aircraft Systems (ICUAS), Dubrovnik,
Croatia, 21–24 June 2022; Volume 3, pp. 421–426. [CrossRef]
231. Fabian, D.; Sebastian, D.; Maximilian, W.; Benjamin, S.; Sandro, W. Reinforcement learning for engineering design automation.
Adv. Eng. Inform. 2022, 52, 101612.
232. Junhyeon, S.; Rakesh, K. Development of an artificial intelligence system to design of structures using reinforcement learning:
Proof of concept. In Proceedings of the AIAA Scitech 2021 Forum, Virtual, 11–15 and 19–21 January 2021; p. 1692.
233. Maximilian, O.; Gordon, W. Design synthesis of structural systems as a Markov decision process solved with deep reinforcement
learning. J. Mech. Des. 2023, 145, 061701.
234. Guan, X.; Xiang, Z.; Bao, Y.; Li, H. Structural dominant failure modes searching method based on deep reinforcement learning.
Reliab. Eng. Syst. Saf. 2022, 219, 108258. [CrossRef]
Buildings 2024, 14, 3515 36 of 36

235. Guan, X.; Sun, H.; Hou, R.; Xu, Y.; Bao, Y.; Li, H. A deep reinforcement learning method for structural dominant failure modes
searching based on self-play strategy. Reliab. Eng. Syst. Saf. 2023, 233, 109093. [CrossRef]
236. Johannes, D.; Lukas, M.; Samuel, Z.; Tarek, I.; Norbert, L.; Dirk, H. Deep reinforcement learning methods for structure-guided
processing path optimization. J. Intell. Manuf. 2022, 33, 333–352.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.