Hindawi

Journal of Electrical and Computer Engineering

Volume 2022, Article ID 3594256, 10 pages
https://doi.org/10.1155/2022/3594256

Research Article
Automatic Intelligent Control System Based on Intelligent
Control Algorithm

Zishan Huang
School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China

Correspondence should be addressed to Zishan Huang; [email protected]

Received 26 February 2022; Revised 18 March 2022; Accepted 28 March 2022; Published 21 April 2022

Academic Editor: Xuefeng Shao

Copyright © 2022 Zishan Huang. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

In order to improve the effect of automatic intelligent control, this paper improves the intelligent vector control algorithm,
analyzes the performance of the algorithm with common power pulses as an example, and obtains an improved intelligent vector
control algorithm suitable for modern intelligent systems. By making two mutually adjacent vectors nonidentical combination in
time, the two vectors have the difference between zero and nonzero, and the vector can be rotated into a certain area. In addition,
with the support of improved algorithms, this paper gets an automated intelligent control system based on intelligent control
algorithms. Finally, this paper verifies the effect of the intelligent control system through experimental research. The analysis of the
test results shows that the automated intelligent control system proposed in this paper has a better effect in intelligent control.

1. Introduction degree of integration and utilization of contemporary

multiple frontier disciplines, multiple advanced technolo-
Traditional control theory is the general term of classic gies, and multiple scientific methods [3].
control theory and modern control theory. Their main The intelligent behavior in the intelligent control system is
feature is model-based control. Traditional control uses essentially a mapping relationship from input to output. When
inaccurate models and certain fixed control algorithms to the input of the system is not an example that has been learned,
place the entire control system under the model framework, it can give a suitable output because of its adaptive function.
which lacks flexibility and adaptability, so it is difficult to be Even when some parts of the system fail, the system can work
competent for the control of complex systems. The core of normally. If the system has a higher degree of intelligence, it can
intelligent control is control decision-making, which uses also automatically find faults and even have the function of self-
flexible decision-making methods to force the control sys- repair, thus reflecting stronger adaptability.
tem to approach the desired goal [1]. Traditional control is It has the function of self-organization and coordination
suitable for solving relatively simple control problems such for complex tasks and scattered sensor information. The
as being linear and time-invariant. These problems can also intelligent controller can make decisions on its own and take
be solved with intelligent methods. Intelligent control is the actions proactively within the scope of the task require-
development of traditional control theory, and traditional ments; and when there is a multitarget conflict, the con-
control and intelligent control can be unified under the troller has the right to make judgments on its own under
framework of intelligent control [2]. The generation of in- certain restrictions. The intelligent control system can learn
telligent control comes from the high complexity and un- the inherent information of the unknown characteristics of a
certainty of the controlled object and the increasingly high process or its environment and use the obtained experience
control performance that people demand. It is a type of for further estimation, classification, decision-making, or
automatic control that can independently drive intelligent control, so as to improve the performance of the system.
machines to achieve their goals without human intervention. That is, it has the ability to learn and acquire new knowledge
In addition, its creation and development require a high about the object and environment during operation and use
2 Journal of Electrical and Computer Engineering

the new knowledge to improve control behavior. The third problem, providing useful exploration. Literature [8] studied
feature of intelligent control is that it can comprehensively the dynamic scheduling method of automatic surface
cross various technologies, making the design of intelligent treatment production line based on multiagent, established
control systems and intelligent controllers increasingly di- an architecture model based on multiagent, and abstracted
versified, and the application scope of intelligent control the complex surface treatment automatic production line
technology is becoming more and more extensive. It is workshop scheduling problem into management, process-
difficult for simple technology to achieve intelligent simu- ing, and workpiece, transports four kinds of agents, focuses
lation, and the combination of multiple technologies is on the analysis of the communication and negotiation
conducive to intelligent simulation; the simple control mechanism between these four agents, studies a tender-bid
method makes the system lack intelligence, and the control mechanism based on the contract network, and optimizes
of integrated adaptive, self-organization, (self)learning, and scheduling through comprehensive indicators. Literature [9]
other technologies can improve the intelligence of the uses a combination of multiagent model and cellular au-
system control. The fourth characteristic of intelligent tomation model to construct a city dynamic model using
control is that it can describe the stability of the system, the geographic information system technology and takes the
controllability and observability of the system, and the actual city as an empirical object, which proves that the
optimal control of the system (that is, the description of the model has a high degree of credibility. Literature [10] uses
entropy function and the energy function) like the tradi- bionics to summarize the structural and functional simi-
tional control theory which analyzes the dynamic charac- larities between the ship formation and the biological im-
teristics of the system, system complexity, etc. The fifth mune system and combines the multiagent theory with the
characteristic of intelligent control is that it is robust and of real biological immune system and proposes a new immune
time, is insensitive to environmental interference and un- multiagent network (IMAN) model and applied it to the
certain factors, can respond to highly abstract discrete symbol cooperative air defense system of the fleet. Literature [11]
commands, and has online real-time response capabilities. established a distributed and coordinated multiagent system
This paper combines the intelligent control algorithm to and applied it to the coordination and optimization of the
study the automated intelligent control system, builds the power system. The system includes multiple power supply
intelligent control system model according to the current agents and management coordination agents. Finally, the
more advanced algorithm model, and verifies the system system is verified by simulation experiments. The feasibility:
function through experimental research. Literature [12] uses multiagent theory to establish a pro-
duction scheduling system, simulates the production
2. Related Work scheduling system according to actual production condi-
tions, and obtains the optimal production scheduling plan,
With the rapid development of artificial intelligence and big which reduces production costs and improves production
data technology, related multiagent technology has also been efficiency. It is useful for the formulation of production
applied in many fields in recent years. Because multiagent scheduling plans. Certain reference value: Literature [13]
technology has the characteristics of reasoning, cooperation, studied the adaptive conditions of distributed structure,
and self-healing, it creates the possibility to solve the centralized structure, and decentralized structure under
problem of complex and dynamic scheduling system. Lit- certain interactive equipment and data resources and further
erature [4] conducted the research on agent-based distrib- explored distributed collaborative solving and centralized
uted dynamic job shop scheduling and proposed a collaborative solving problems. Literature [14] explored the
multiagent distributed dynamic job shop scheduling scheme control problem of the agent network with a fixed topology
based on contract network protocol bidding mechanism; and finally proved through simulation experiments that the
literature [5] analyzed agent-based technology distributed method based on the consensus protocol can be successfully
job shop scheduling structure, proposes the concept of applied to the multiagent formation control, and the effect
autonomous scheduling execution, and provides an au- is better. Literature [15] studied the dynamic scheduling
tonomous scheduling execution algorithm based on dis- strategy of multiagent production line based on MDP.
turbance analysis, so that the scheduling execution agent can Aiming at the dynamic task allocation problem of work-
autonomously make rapid and optimal decisions on system shop production line, based on Markov decision process
disturbances. Literature [6] proposes to use multiagent theory, a dynamic task scheduling mathematical model of
negotiation to solve the problem of intelligent transfer multiagent production line was established. Literature [16]
conflicts and finally designs a kind of information that can carried out modeling, optimization, and simulation re-
solve the problem of virtual enterprise transfer conflicts search on the production line based on multiagent, built the
through rational and efficient use of the agent’s scheduling, model through Simulink/Stateflow simulation tool and
collaboration, and intelligence characteristics. Integrated conducted experimental research, and proposed related
system: Literature [7] studied the agile production line control strategies according to the actual production sit-
scheduling based on multiagent, combined with the latest uation. The communication program is written by VC
theoretical results of many technologies in the field of language, and the distributed simulation of the multiagent
computer and artificial intelligence, applied multiagent system is completed. Finally, through statistics and analysis
technology to the solution field of agile production line of simulation data, the production line optimization
scheduling, and solved the actual production scheduling strategy is verified.
Journal of Electrical and Computer Engineering 3

3. Vector Control Based on Intelligent According to the above equivalent relationship, the
Control Algorithm structure diagram shown in Figure 1 can be obtained. It
can be seen from Figure 1 that the vector control input is
When researching the multimodal control algorithm, it is three-phase power A, B, and C. To obtain a DC motor,
necessary to use the MATLAB/Simulink platform to build which is input by id and iq and output by ω, it is necessary
the simulation model of this variable structure AC servo to perform Park conversion and Clarke conversion
pressurization system. If we want to build a physical model according to the oriented rotor flux [17].
of an AC motor, we should understand its characteristics.
One is a nonlinear system, the other is a strongly coupled
system, and the third is a high-order system, all of which are 3.1. Clarke Transformation (3S/2S Transformation). There
multivariable. These characteristics indicate that it should be are two types of Clarke transformation: equal-amplitude
expressed by nonlinear formulas, which is very inconvenient vector transformation and equal-power vector transfor-
when controlling such systems. The main reason for the mation. If equal-amplitude vector transformation is used,
complexity of the AC motor model is the coupling between compensation needs to be added in the later Park trans-
the magnetic flux and the magnetic flux. If the motor model formation. Therefore, the Clarke transformation used this
is decomposed into a model controlled separately by torque time is an equal-power transformation method. The fol-
and flux linkage, then it can be simulated as a DC motor lowing two points must be done in the constant power
control model to control a non-DC motor. Vector control coordinate transformation:
can achieve the abovementioned control effect. (a) The effect of the magnetic field generated by the
The principle of vector control is to measure the stator current before and after the coordinate transfor-
current vector of the motor and to decompose the stator mation remains unchanged.
current through the basic principle of the magnetic field, so
as to realize the control of the motor. The specific method is (b) The power of the motor before and after the coor-
to decompose the current vector into the torque current and dinate transformation remains at the original value.
the excitation current and then control them. The control The vector u and current i in the original coordinates are
here refers to controlling the amplitude and phase of the transformed into u′ and current i′ in the new coordinates.
current component of the magnetic field and the torque Since we want them to have the same transformation matrix
current component. This control method is a vector control C, then [18]
method. Therefore, the vector control strategy is introduced
to the simulation of the motor when doing the optimization u � Cu′ ,
(1)
algorithm part this time. Coordinate transformation is a very i � Ci′ .
critical link in vector control technology. Only by trans-
forming its coordinates can the motor torque and flux In order to realize the inverse transformation, the
linkage be decoupled. transformation matrix C must have an inverse matrix C−1 , so
Coordinate transformation is the core step of AC motor the transformation matrix C must be a square matrix, and
vector control and an important mathematical method to the value of its determinant must not be equal to zero.
simplify the complex physical model of the motor. The Because u � zi, z is the impedance matrix,
purpose of coordinate transformation is to transform the
physical model of an AC motor into a model similar to a DC u′ � C−1 u
motor. The AC motor model after coordinate transforma-
� C−1 zi
tion is more convenient for analysis and control. (2)
The essence of coordinate transformation is to replace � C−1 zCi′
the original variables in the formula with a set of new
� z′ i′ .
variables obtained after transformation. It is based on the
principle of generating the same rotating magnetomotive In the above formula, the changed impedance matrix is
force. The variable in the three-phase stator coordinate represented by z′ , which can be expressed as
system is equivalent to the variable αβ0 in the two-phase
stationary coordinate system through Clarke transfor- z′ � C−1 zC. (3)
mation, which is equivalent to the alternating currents iα
and iβ . Through the Park transformation, the variable αβ0 In order to follow the principle of constant power
in the two-phase stationary coordinate system can be consumption, the electrical power consumption iT u � u1 i1 +
equivalent to the variable dq 0 in the two-phase rotating u2 i2 + · · · un in under one coordinate is equal to the electrical
coordinate system, which is equivalent to the DC currents power consumption iT′ u′ � u1′i1′ + u2′i2′ + · · · un′in′ under the
id and iq . The variable ABC in the three-phase stator other coordinate, namely [19]:
coordinate system, the variable αβ0 in the two-phase static
coordinate system, and the variable dq0 in the two-phase iT u � iT u′ , (4)
rotating coordinate system are three commonly used
T ′
coordinate systems in the vector control of AC motors. iT u � Ci′ 􏼁 Cu′ � iT CT Cu′ . (5)
4 Journal of Electrical and Computer Engineering

A B C β
B

iC iA
iB
N2iβ
N3iB
3/2

iβ iα
Asynchronous
motor φ A
N3iA N2iα
VR

iq id N3iC

Equivalent DC C
motor model
Figure 2: Vector coordinate system.

three-phase motor and a two-phase motor. Formulas (7) and

ω (8) are expressed by matrix, namely:
1 1 i
iα ⎡⎢⎢⎢ 1 −2 −2 ⎤⎥⎥⎥⎡⎢⎢ α ⎤⎥⎥
⎢
⎢ ⎥
⎥⎥⎢ ⎥⎥⎥
⎥ ⎢
⎢
Figure 1: Coordinate transformation structure diagram of motor. ⎡⎢⎢⎢⎣ ⎤⎥⎥⎥⎦ � N3 ⎢⎢⎢
⎢⎢⎢ √� √� ⎥⎥⎥⎥⎢⎢⎢⎢⎢ iβ ⎥⎥⎥⎥⎥. (9)
iβ N2 ⎢⎢⎢ ⎥⎥⎥⎢⎢⎣ ⎥⎥⎦
⎣ 3 3 ⎦
In order to make formula (4) the same as formula (5), the 0 − iC
2 2
transformation matrix c should be an orthogonal matrix. 1 −1/2 −1/2
In the above formula, C−1 is the inverse matrix of C; iT is the The transformation matrix 􏼢 √� √� 􏼣 cannot
0 3 /2 − 3 /2
transposedmatrixofi;iT′ isthetransposed matrixofi′ ;CT isthe be changed inversely, because it is a nonsquare matrix. To this
transposed matrix of C; I is the identity matrix; Z and Z′ are end, it is necessary to introduce the zero-axis current, that is,
impedance matrices, respectively; u, u′ , i, i′ are the vector and an unrestricted nonoriginal variable i0 of iα and iβ . In the
current column and row matrix, respectively. At the same time,
formed α − β − 0-axis coordinate system, the zero axis is
according to the matrix algorithm, there are C−1 C � I;
perpendicular to the α and β axes at the same time. We define
(Ci′ )T � iT′ CT; (KC)T � KCT ; u � Cu′ , and u′ � C−1 u.
Figure 2 is the relative positional relationship of the
magnetic potential vector. The magnetic potential vectors N2 i0 � k N3 iA + N3 iB + N3 iC 􏼁, (10)
are the magnetic potential vectors of the nonrotor three-
phase motor windings A, B, and C and the magnetic po- N3
i0 � k i + i + i 􏼁. (11)
tential vectors of the two-phase motor windings α and β, N2 A B C
respectively. The A axis coincides with the α axis. It can be
In the formula, k is the undetermined coefficient.
known from the vector coordinate transformation principle
Therefore, formula (10) is rewritten as
that the two are completely equal magnetic fields; that is, the
resultant magnetic potential vector has equal components 1 1
on the two position and space axes. iα ⎢⎢⎢⎡ 1 −2 −2 ⎥⎥⎥⎤ iA
⎡⎢⎢⎢ ⎤⎥⎥⎥ ⎢⎢⎢ ⎥⎥⎥⎡⎢ ⎤⎥
Therefore, there are ⎢⎢⎢ ⎥⎥⎥ N3 ⎢⎢⎢⎢ √� √� ⎥⎥⎥⎥⎥⎢⎢⎢⎢⎢ ⎥⎥⎥⎥⎥
⎢⎢⎢ iβ ⎥⎥⎥ � ⎢ ⎥⎢ ⎥
N2 � N3 iA + N3 iB cos 120° + N3 iC cos −120° 􏼁, ⎢⎢⎢ ⎥⎥⎥ N ⎢⎢⎢⎢⎢ 0 3 − 3 ⎥⎥⎥⎥⎥⎢⎢⎢⎢⎢ iB ⎥⎥⎥⎥⎥. (12)
⎣ ⎦ 2⎢ ⎢⎢⎢ 2 2 ⎥⎥⎥⎥⎣ ⎦
(6) ⎢⎣ ⎦ i
N2 iβ � 0 + N3 iB sin 120° + N3 iC sin −120° 􏼁. i0 C
k k k
That is:
In the formula, the matrix C is defined as
N 1 1
iα � 3 􏼔iA − iB − iC 􏼕, (7) 1 1
N2 2 2 ⎢⎢⎢⎡ 1 −2 −2 ⎤⎥⎥⎥
⎢⎢⎢ ⎥⎥⎥
√� √� ⎢⎢⎢⎢ ⎥⎥⎥
⎥
N3 3 3 N3 ⎢⎢⎢⎢ √� √� ⎥⎥⎥⎥
iβ � 􏼢0 + iB − i 􏼣. (8) C� ⎢⎢⎢ 3 3 ⎥⎥⎥⎥. (13)
N2 2 2 C N2 ⎢⎢⎢ 0 − ⎥
⎢⎢⎢
⎢⎢⎢ 2 2 ⎥⎥⎥⎥⎥
⎥⎥⎥
In the formula, N2 and N3 , respectively, represent the ⎢⎣ ⎦
effective number of turns of each phase of the stator of a k k k
Journal of Electrical and Computer Engineering 5

The transpose matrix CT of C is 1 1

⎡⎢⎢⎢ 1 −2 −2 ⎤⎥⎥⎥
1 0 k ⎢⎢⎢ ⎥⎥⎥
⎢
⎡
⎢ ⎥⎥⎤⎥ iα iA ⎢⎢⎢ ⎥⎥⎥ iA
⎢
⎢
⎢
⎢
⎢ √� ⎥⎥⎥
⎥⎥⎥ ⎡⎢⎢⎢ ⎤⎥⎥⎥ ⎡⎢⎢⎢ ⎤⎥⎥⎥ 􏽲�⎢⎢⎢⎢ √� √� ⎥⎥⎥⎥⎥⎡⎢⎢⎢ ⎤⎥⎥⎥
⎢ ⎢⎢⎢ ⎥⎥⎥ ⎢ ⎥ ⎢ 3 ⎥⎥⎥⎥⎢⎢⎢⎢ ⎥⎥⎥⎥
⎢
⎢ 1 3 ⎥ ⎢⎢⎢ iβ ⎥⎥⎥ � C⎢⎢⎢⎢⎢ iB ⎥⎥⎥⎥⎥ � 2⎢⎢⎢⎢⎢ 0 3
T N3 ⎢
⎢
⎢
⎢ − k ⎥⎥⎥⎥⎥ ⎢⎢⎢ ⎥⎥⎥ ⎢⎢⎢ ⎥⎥⎥ 3⎢⎢ ⎢
⎢ 2
− ⎥⎢⎢ iB ⎥⎥.
2 ⎥⎥⎥⎥⎥⎢⎢⎢⎣ ⎥⎥⎥⎦
(19)
C � ⎢
⎢ 2 2 ⎥⎥⎥. (14) ⎣ ⎦ ⎣ ⎦ ⎢⎢⎢
N2 ⎢
⎢
⎢
⎢ ⎥⎥⎥ ⎢⎢⎢
⎥⎥⎥
⎥⎥⎥ i
⎢
⎢
⎢ ⎥⎥⎥ i0 iC ⎢⎢⎢
⎢ √ � ⎥ C
⎢
⎢
⎢
⎣ 1 3 ⎥⎦
⎥⎥ ⎣ 1 1 1 ⎥⎥⎦
√� √� √�
− − k 2 2 2
2 2
The inverse matrix C−1 of C is
1 3.2. Park Transformation (2s/2r Transformation).
1 0
⎢
⎡
⎢
⎢
⎢
⎢ 2k ⎤⎥⎥⎥⎥⎥ Generally speaking, the 2s/2r conversion refers to the
⎢
⎢
⎢ ⎥⎥⎥
⎢
⎢
⎢ ⎥⎥⎥ conversion between the two-phase nondynamic coordinate
⎢ √� ⎥⎥
2N2 ⎢
⎢
⎢
⎢ 1 3 1 ⎥⎥⎥⎥ system and the two-phase rotating coordinate system. To
C−1 � ⎢
⎢ − ⎥⎥. (15)
3N3 ⎢
⎢
⎢
⎢
⎢ 2 2 2k ⎥⎥⎥⎥ obtain the rotating magnetomotive force, two-phase non-
⎢
⎢
⎢ ⎥⎥⎥ dynamic winding is required, and two-phase balanced
⎢
⎢
⎢ ⎥⎥⎥
⎢
⎢ √� ⎥⎥ nondirect current is added to it. If the two-phase windings
⎢
⎣ 1 3 1 ⎥⎦
− − whose rotational angular velocity is equal to the rotational
2 2 2k angular velocity of the synthesized magnetomotive force are
In order to comply with the principle of constant power turned, then the space-rotating magnetomotive force is
conversion, CT � C−1 is known. That is, the above formula generated in the two-phase winding with nonalternating
(14) is equal to the formula (15); then: current.
Figure 3 shows the Park transformation relationship
2N2 N3 1 diagram, and the Park transformation is derived from Clark
� ; � k. (16)
3N3 N2 2k transformation as
We can obtain separately ⎨ ud cos α + uq sin α � uα ,
⎧
􏽲� ⎩ u sin α − u cos α � u , (20)
N3 2 d q β
� ,
N2 3
(17) uα cos α sin α ud
􏽲� 􏼠 􏼡 �􏼠 􏼡􏼠 􏼡. (21)
1 uβ sin α −cos α uq
k� .
2
From formula (20), we can get
By substituting formula (17) into formula (13) and 2
formula (15), then ⎪
⎧
⎨ ud cos α + uq sin α cos α � uα cos α,
⎪ (22)
⎩ u sin2 α + u sin α cos α � u sin α.
1 1 d q β
⎢
⎡
⎢ 1 − ⎥⎥⎥⎤ −
⎢
⎢
⎢ 2 ⎥⎥⎥ 2
⎢
⎢ ⎥⎥⎥ By adding the two types, there are
⎢
⎢
⎢
⎢
⎢
⎢
⎢ √� √� ⎥⎥⎥⎥⎥ ud � uα cos α + uβ sin α,
⎢
⎢ 3 3 ⎥⎥⎥
C �⎢
⎢
⎢
⎢ 0 − ⎥⎥⎥,
⎢
⎢
⎢ 2 2 ⎥⎥⎥ ⎪
⎧ 2
⎢
⎢
⎢ ⎥⎥⎥ ⎨ ud cos α sin α + uq sin α � uα sin α, (23)
⎢
⎢ ⎥⎥⎥
⎢
⎢
⎢ ⎥⎥ ⎪
⎩ u cos α sin α − u cos2 α � u cos α.
⎢
⎣ 1 1 1 ⎥⎥⎦ d q β
√� √� √�
2 2 2
By adding the two formulas, we get
(18)
1 uq � uβ cos α − uα sin α, (24)
⎢
⎡
⎢ 1 0 √� ⎤⎥⎥⎥
⎢
⎢
⎢ 2 ⎥⎥⎥
⎢
⎢
⎢ ⎥⎥⎥
⎢
⎢ ⎥⎥⎥ and we get
􏽲 �⎢
⎢
⎢ 1 √�
⎢ ⎥⎥⎥
2⎢
⎢
⎢ 3 1 ⎥⎥⎥ ud cos α sin α uα
C−1 � ⎢
⎢
⎢ − √� ⎥⎥⎥. ⎝
⎛ ⎠ �􏼠
⎞ ⎝ ⎠,
3⎢
⎢
⎢ 2 2 2 ⎥⎥⎥ 􏼡⎛ ⎞
⎢
⎢
⎢ ⎥⎥⎥ uq −sin α cos α uβ
⎢
⎢
⎢ ⎥⎥⎥ (25)
⎢
⎢
⎢ √� ⎥⎥⎥
⎢
⎢
⎢ ⎥⎥⎦ ism cos α sin α isa
⎣ 1 3 1
− − √� 􏼠 􏼡 �􏼠 􏼡􏼠 􏼡.
2 2 2 ist −sin α cos α isb
Therefore, the Clarke transformation (or 2/3 transfor- Park is inversely transformed into the inverse matrix of
mation) formula is matrix (29):
6 Journal of Electrical and Computer Engineering

β axle +
T1 T3 T5

b axle d axle
A N
B C

a axle T4 T6 T2
α angle α axle

q axle
-
c axle
Figure 4: Inverter circuit.
Figure 3: Park transformation relationship diagram.

⎪
⎧ UA (t) � Um cos(θ),
⎪
⎪
⎪
⎪
cos α −sin α ⎪
⎪
C−1
park � 􏼠 􏼡. (26) ⎪
⎪
sin α cos α ⎪ U (t) � U cos􏼠θ − 2π􏼡,
⎪
⎨ B m
⎪ 3 (27)
The function of space vector pulse width modulation ⎪
⎪
⎪
⎪
(SVPWM) is to make the output waveform closer to a sine ⎪
⎪
⎪
⎪ θ − 2π
waveform. The specific method is as follows: a three-phase ⎪
⎪
⎩ UC (t) � Um cos􏼠 􏼡.
power inverter is composed of six power switching elements, 3
and the switching mode is appropriately switched to control
In the formula, θ � 2πft; then the resultant space vector
the generation of a pulse width modulated wave. Compared
U(t) added by the three-phase vector space vector can be
with the traditional pulse width modulation technology, it
expressed as
has the advantages of reducing the motor torque pulsation to
a certain extent, and the rotation trajectory is closer to the 3
U(t) � UA (t) + UB (t)ej2π/3 + UC (t)ej4π/3 � Um ejθ . (28)
circular flux trajectory. 2
The space vector pulse width modulation technology
uses the principle of average equivalent utility as the basis of According to the above, U(t) is a rotating space vector
theoretical analysis; that is, by combining the basic vector whose amplitude is 1.5 times the peak value of the phase
vectors in a single open and closed cycle, the average vector vector, and Um is the peak value of the phase vector, and the
is equal to the given vector. At a certain moment, by making space vector rotates at an angular frequency ω � 2πf in the
two mutually adjacent vectors carry out a nonidentical counterclockwise direction at a uniform speed. The pro-
jection of the space vector U(t) on the three-phase coor-
combination in time, the two vectors have a difference
dinate axis (a, b, c) is the symmetrical three-phase sine. Since
between zero and nonzero, and the vector can be rotated into
the inverter’s three-phase bridge arm is composed of 6
a certain area. In order to obtain the PWM waveform, the
opening and closing tubes, in order to explore the space
action time of the two vectors can be added multiple times,
vector output by the inverter when the upper and lower arms
and the timing of the addition is within a complete sampling
of each phase are opened and closed in different combi-
time period. In this way, the action time of each vector can be
controlled, and a space vector rotating according to a cir- nations, the opening and closing expression Sχ (χ � a, b, c) is
cular trajectory can be obtained. The actual magnetic flux specifically described as
close to the ideal magnetic flux circle is generated by 1, Upper bridge arm conduction,
changing the open and closed state of the inverter, and then Sχ � 􏼨 (29)
0, Lower bridge arm conduction.
the switching state of the inverter is determined by the
comparison result of the two. Figure 4 shows the inverter There are eight possible combinations of (Sa , Sb , Sc ),
circuit. including 6 nonzero vectors U1 (001), U2 (010), U3 (011),
Udc is the non-AC bus side vector, and the three-phase U4 (100), U5 (101), U6 (110) and two zero vectors U0 (000)
vectors output by the inverter are UA , UB , and UC , re- and U7 (111).
spectively, which form an arrangement of 120° on each other The magnitude modulus of a nonzero vector is 2Udc /3,
in space, and the coordinate system is a three-phase plane the distance between two adjacent vectors is 60° , and the
nondynamic coordinate system. Three nonplanar vectors magnitude of the two zero vectors at the center of the sector
UA (t), UB (t), and n UC (t) can be defined. The directions of is zero. The components of any vector in each sector are
the three are always on the reference line of each phase, and taken from the two vectors and the zero vector that are
the magnitude is changed with time according to the sine adjacent to each other in each sector. The resultant vector is
law, and the time phase differs by 120° . If it is assumed that T Tx Tx +Ty T
the effective value of the phase vector is Um and the power 􏽚 Uref dt � 􏽚 Ux dt + 􏽚 Uy dt + 􏽚 U∗0 dt. (30)
supply frequency is f, then the formula can be obtained: 0 0 Tx Tx +Ty
Journal of Electrical and Computer Engineering 7

B axis
Embedded intelligent terminal
opens the core service

(110)
(010)
Section 2 Coordinator and Zigbee control
nodes enter the network
Section 3 Section 1
(111)
(011)
(000)
(100)
Section 4 Section 6 Actively report the collected data
during the control node cycle
Section 5
(001)

Analyse the received underlying

data and store it

Figure 5: Vector pie chart. The intelligent control module

processes the data information for
the controlled object
Zigbee
network

User
Establish private form control
Serial Junction Control instructions and issue them
Interface station node

Embedded intelligent
terminal

Controlled The actuator performs the control

plant instruction

Figure 7: The control flow of the intelligent control system.

Coordinator nonzero vectors and zero vector in the area to synthesize the
vector as a small increase. The tentative vector obtained by a
Router small increase each time is equivalent to a vector space
Terminal
vector, and the vector space vector plane can be used for
instrument smooth rotation of the vector to achieve the purpose of pulse
Figure 6: The overall architecture of the intelligent control system. width modulation of the vector.

4. Automatic Intelligent Control System

Among them, Uref is the expected vector; T is the Based on Intelligent Control Algorithm
sampling time; Tx , Ty , and T0 , respectively, correspond to
the action time of the two nonzero vectors Ux , Uy and the The overall architecture design is the first step to complete
zero vector U0 in one cycle. Among them, U0 includes two the design and realization of the intelligent control system. It
zero vectors, U0 and U7 . The meaning of formula (30) is that points out the working principle and control flow of the
the sum of integral effect produced by vector Uref in time T is entire system. The software and hardware platforms
the same as the sum of integral effects produced by values implemented by the system determine the functional
Ux , Uy , and U0 in times Tx , Ty , and T0 , respectively. characteristics of the system, and the design of the com-
The equivalent rotation vector is usually a combination munication protocol specifies all the data formats in the
of a three-phase sine wave vector in a vector space vector. system. The system is mainly composed of an embedded
The input power angle frequency is its rotation speed, and its intelligent terminal and a wireless sensor network. The
trajectory is shown in Figure 5. controlled object is placed within the coverage of the wireless
Using the abovementioned vector synthesis technique, a sensor network, and the embedded intelligent terminal
three-phase sine wave vector can be obtained. The acqui- communicates with the wireless sensor network through a
sition method is to use the set vector to start from position serial port. The overall system architecture is shown in
U4 (100) on the vector space vector and use the two adjacent Figure 6.
8 Journal of Electrical and Computer Engineering

Serial port connected to the Store in the

coordinator N Exist?
database
Y
CRC2, CRC1 Device number
verification Assign the
device
number Correct it to the
Exception Correct Equipment number N device number in
code 05 N verification? matching? the database
Fn=02
Y Y

Session Fn=01 Fn=02

ID 0xFFFF
Net data
Generates
Functional
response data
code FC 66

Serial port connected to

Node
the coordinator
address

Figure 8: The flowchart of terminal processing of network access data.

Serial port connected to the

coordinator

CRC2, CRC1
verification Discard data N Exist?

Exception Correct Device number

code 05 N verification?
Discard data

Y
Equipment number N
Session matching?
ID 0xFFFF CollectionDataTable
Take the initiative SensorTableOperate
to report data class processing Y Operate
class processing
Functional
code FC 66 Sensor type
matching? Y Ignoring data

Node
address N

Delete the database

plains record
Sensor type,
data

Sensor type

Store in the
database

Figure 9: The flowchart of the terminal processing the actively reported data.
Journal of Electrical and Computer Engineering 9

The overall control flowchart of the intelligent control 98

system in this paper is shown in Figure 7. The specific 97
96
control process is as follows: (1) The embedded intelligent 95
terminal performs initialization operations and starts core

Evaluation
94
services. (2) The embedded intelligent terminal is connected 93
to the convergence point through the serial port, so that the 92
91
coordinator can access the network. After the coordinator 90
accesses the network, it accesses the control node, so that the 89
control node accesses the network. (3) The sensor collects 88
87
the data information of the controlled object, and after
0 50 100 150 200
relevant processing such as A/D conversion of the control
node, it actively periodically reports it to the embedded Num
intelligent terminal according to the ZigBee private com- Figure 10: Evaluation of the intelligent effect of intelligent vector
munication protocol format. (4) After the embedded in- control algorithm.
telligent terminal receives the data from the ZigBee network,
it is handed over to the parsing module for processing, and
94
the network data is distinguished from the data reported 93
actively according to the function code. In the network 92
access data, it extracts ZigBee network equipment infor- 91
90

Evaluation
mation and stores it in the net equipment table of the da-
89
tabase. The sensor data information and collected data
88
information are extracted from the actively reported data 87
and stored in the sensor table and collection data table, 86
respectively, in the database. (5) It extracts the specific data 85
information of the controlled object from the collected data 84
83
and obtains the control vector corresponding to the current
0 50 100 150 200
data through the offline look-up table method of the fuzzy
intelligent control algorithm. (6) It encapsulates the ob- Num
tained control vector into a control command in the ZigBee Figure 11: Evaluation of intelligent control effect of automated
private communication protocol format and sends it to the intelligent control system.
corresponding device in the underlying sensor network. (7)
The corresponding device at the bottom layer receives the
control instruction, and after D/A conversion and other Through the above experimental analysis, it can be seen
processing, the corresponding analog vector is output from that the automated intelligent control system proposed in
the AO output interface of the control node and added to the this paper has a better effect in intelligent control, and the
control unit to realize real-time control of the controlled embedded intelligent system of this paper can be applied to
object. multiple systems with intelligent control requirements.
Embedded intelligent terminals play a central role in the
entire intelligent control system. The specific content can be 5. Conclusion
seen in Figure 8. The interface between it and the coordi-
nator is a serial port, which realizes the realization of the One of the characteristics of intelligent control is that it is
intelligent control function of the system by collecting in- suitable for uncertain or difficult-to-define process control,
formation from the control node, intelligently analyzing the complex nonlinear controlled object control, and time-
information, and intelligently issuing control commands. varying process control. As a complex model, the description
If the node exists and matches, the actively reported data can be quantitative (number or parameter) or qualitative
will be handed over to the two processing database sub- (causal relationship) description. The second characteristic of
classes for processing. Figure 9 shows the process of the intelligent control is that it uses self-adaptation, self-orga-
smart terminal processing the actively reported data. nization, self-learning, and other methods to improve the
Through the above research, the performance verifica- automation and intelligent control of the system. This enables
tion of the intelligent control system in this paper is carried it to process various uncertain, qualitative information and
out. First, the algorithm effect evaluation of the intelligent data structures, as well as unstructured information and data,
vector control algorithm proposed in this paper is carried process and utilize knowledge of different natures, identify
out. The statistical test results are shown in Figure 10. changes in the structure or composition of the main control
Through the above research, it can be seen that the system, and modify or reconstruct its own parameters or
intelligent vector control algorithm proposed in this paper structure according to changes in the main control system or
has a good intelligent effect, and then the evaluation of environment. In addition, it is also fault-tolerant, capable of
intelligent control effect of the automatic intelligent control self-diagnosing, shielding, and self-recovering various faults.
system is carried out, and the result shown in Figure 11 is This paper combines the intelligent control algorithm to
obtained. study the automated intelligent control system, builds the
10 Journal of Electrical and Computer Engineering

intelligent control system model according to the current [11] L. Peng and Z. Jiang, “Intelligent automatic pig feeding system
more advanced algorithm model, and verifies the system based on PLC,” Revista Cientı́fica de la Facultad de Ciencias
function through experimental research. Veterinarias, vol. 30, no. 5, pp. 2479–2490, 2020.
[12] S. Anila, B. Saranya, G. Kiruthikamani, and P. Devi, “Intel-
ligent system for automatic railway gate controlling and
Data Availability obstacle detection,” International Journal Of Current Engi-
neering And Scientific Research (IJCESR), vol. 4, no. 8,
The labeled dataset used to support the findings of this study pp. 2394–0697, 2017.
is available from the corresponding author upon request. [13] L. B. Prasad, H. O. Gupta, and B. Tyagi, “Intelligent control of
nonlinear inverted pendulum system using Mamdani and
Conflicts of Interest TSK fuzzy inference systems: a performance analysis without
and with disturbance input[J],” International Journal of In-
The author declares no competing interests. telligent Systems Design and Computing, vol. 2, no. 3-4,
pp. 313–334, 2018.
Acknowledgments [14] J. Yang, P. Wang, W. Yuan, Y. Ju, W. Han, and J. Zhao,
“Automatic generation of optimal road trajectory for the
This study was sponsored by Hubei University of rescue vehicle in case of emergency on mountain freeway
Technology. using reinforcement learning approach,” IET Intelligent
Transport Systems, vol. 15, no. 9, pp. 1142–1152, 2021.
[15] X. Yao, J. H. Park, H. Dong, L. Guo, and X. Lin, “Robust
References adaptive nonsingular terminal sliding mode control for au-
tomatic train operation,” IEEE Transactions on Systems, Man,
[1] V. Syrotiuk, S. Syrotyuk, V. Ptashnyk et al., “A hybrid system and Cybernetics: Systems, vol. 49, no. 12, pp. 2406–2415, 2018.
with intelligent control for the processes of resource and [16] M. J. Mahmoodabadi and M. Taherkhorsandi, “Intelligent
energy supply of a greenhouse complex with application of control of biped robots: optimal fuzzy tracking control via
energy renewable sources,” Przeglad Elektrotechniczny, multi-objective particle swarm optimization and genetic al-
vol. 96, no. 7, pp. 149–152, 2020. gorithms,” AUT Journal of Mechanical Engineering, vol. 4,
[2] L. Vladareanu, V. Vladareanu, H. Yu, D. Mitroi, and no. 2, pp. 183–192, 2020.
A.-C. Ciocı̂rlan, “Intelligent control interfaces using e mul- [17] W. He, Z. Li, and C. L. P. Chen, “A survey of human-centered
tidimensional theory applied on VIPRO platforms for de- intelligent robots: issues and challenges,” IEEE/CAA Journal
veloping the IT INDUSTRY 4.0 concept,” IFAC- of Automatica Sinica, vol. 4, no. 4, pp. 602–609, 2017.
PapersOnLine, vol. 52, no. 13, pp. 922–927, 2019. [18] Y. Huang, S. Liu, C. Zhang, X. You, and H. Wu, “True-data
[3] P. Zheng, J. Zhang, H. Liu, J. Bao, Q. Xie, and X. Teng, “A testbed for 5G/B5G intelligent network,” Intelligent and
wireless intelligent thermal control and management system Converged Networks, vol. 2, no. 2, pp. 133–149, 2021.
for piglet in large-scale pig farms,” Information Processing in [19] H. Dong, C. Roberts, Z. Lin, and F.-Y. Wang, “Guest editorial
Agriculture, vol. 8, no. 2, pp. 341–349, 2021. introduction to the special issue on intelligent rail trans-
[4] M. Nadafzadeh and S. Abdanan Mehdizadeh, “Design and portation,” IEEE Transactions on Intelligent Transportation
fabrication of an intelligent control system for determination Systems, vol. 20, no. 7, pp. 2677–2680, 2019.
of watering time for turfgrass plant using computer vision
system and artificial neural network,” Precision Agriculture,
vol. 20, no. 5, pp. 857–879, 2019.
[5] A. P. Araújo Neto, G. W. Farias Neto, T. G. Neves, W. Ramos,
and K. Brito, “Changing product specification in extractive
distillation process using intelligent control system,” Neural
Computing & Applications, vol. 32, no. 17, pp. 13255–13266,
2020.
[6] Y. Arya, “Automatic generation control of two-area electrical
power systems via optimal fuzzy classical controller,” Journal
of the Franklin Institute, vol. 355, no. 5, pp. 2662–2688, 2018.
[7] N. Harrabi, M. Souissi, A. Aitouche, and M. Chaabane,
“Intelligent control of grid-connected AC-DC-AC converters
for a WECS based on T-S fuzzy interconnected systems
modelling,” IET Power Electronics, vol. 11, no. 9,
pp. 1507–1518, 2018.
[8] H. Yang, A. Alphones, Z. Xiong, D. Niyato, J. Zhao, and
K. Wu, “Artificial-intelligence-enabled intelligent 6G net-
works,” IEEE Network, vol. 34, no. 6, pp. 272–280, 2020.
[9] M. Al-Khafajiy, S. Otoum, T. Baker et al., “Intelligent control
and security of fog resources in healthcare systems via a
cognitive fog model,” ACM Transactions on Internet Tech-
nology, vol. 21, no. 3, pp. 1–23, 2021.
[10] L. Haibo, L. Zhenglin, and L. Guoliang, “Neural network
prediction model to achieve intelligent control of unbalanced
drilling’s underpressure value,” Multimedia Tools and Ap-
plications, vol. 78, no. 21, pp. 29823–29851, 2019.