Scribd
Upload
326 views

Taguchi's Technique For Quality Improvement

The document summarizes Taguchi's technique for quality improvement. It discusses Taguchi's definition of quality as minimizing societal loss from a product. It presents the quality loss function and describes robust design as reducing variability from noise factors. Experiments are designed using orthogonal arrays to efficiently test multiple factors and interactions. Examples demonstrate assigning factors to arrays and analyzing results to identify significant sources of variability.

Uploaded by

Eangals Vishnu
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
326 views

Taguchi's Technique For Quality Improvement

The document summarizes Taguchi's technique for quality improvement. It discusses Taguchi's definition of quality as minimizing societal loss from a product. It presents the quality loss function and describes robust design as reducing variability from noise factors. Experiments are designed using orthogonal arrays to efficiently test multiple factors and interactions. Examples demonstrate assigning factors to arrays and analyzing results to identify significant sources of variability.

Uploaded by

Eangals Vishnu
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 31

Taguchi’s Technique for

Quality improvement
Dr. Genichi Taguchi

• Widely acknowledged leader in


the U.S. industrial quality movement.
• Credited for starting the “Robust Design”
movement in Japan in 1950’s.
• Helped correct postwar Japan's telephone
system.
• 1980 introduced Taguchi method to AT&T.
The Taguchi Technique
 Quality
 Quality Loss Function

 Robust Design
The Taguchi definition of quality
 The quality of product is the minimum loss
imparted by the product to society from the time
the product is shipped
 What is loss
 Returns
 Warrant
 Customer complaint
 Time and money spent by the customer
 Eventual loss of market share
Quality characteristics

 Nominal-the-best
 Smaller- the –better
 Larger-the-better
Quality Loss
 The traditional model for quality losses
 No losses within the specification limits!
Cost
Scrap Cost
LSL Target USL

• The Taguchi loss function


– the quality loss is zero only if we are on target
Quality Loss Function
 Nominal the best
 L (y) = k (y –m)2
 Smaller the better
 L(y) = k (y)2
 Larger the better
 L (y) = k (1/ y2 )
 Y = value of the characteristics
 L(y) = The loss in Rs. per piece
 M = the target value
Reducing Quality loss through
reducing variance
 Screening out bad products
 Discovering and eliminating the causes of
discrepancy
 Narrowing the tolerance
 Application of robust design
Types of factors/parameters
 Control factors
 Parameters whose values are controlled by
design engineer
 Noise factors
 Causes deviations of quality characteristics
from target. These are difficult to control
Variability due to Noise
 External noise
 Internal noise
 Unit to unit noise
Principle of robustization
 Attempt to reduce loss due to noise factors
inherent in any system by considering
control factors
 Attempt to reduce σ2
Robust design
 System design
 Require technical knowledge
 The process of examining competing technologies for
producing a product - Includes choices of technology
and process design
 Parameter design
 Involves determination of parameter values that are
least sensitive to noise
 Use of experimental design methods
 Tolerance design
 Improves the quality by narrowing tolerances on the
process or product parameters
 The focus of Taguchi is on Parameter design
Steps in robust design of
experiments
 Define the problem
 Determine the objective
 Define the quality characteristics
 Design the experiment
 Selection of factors and interaction
 Selection of number of levels of the factors, range of
factor levels
 Selection of Orthogonal Array (OA)
 Assignment of factors and interaction to OA column
 Perform the experiment
 Analyze the experiment
 Verifying the experiment result
Orthogonal array
 An orthogonal array is a matrix of numbers
arranged in columns and row
 Each column represents a specific factor
 Each row represents the state of the factors in a
given experiment
 The levels of the various factors are balanced and
can be separated from the effects of the other
factors within experiment
Orthogonal array L 8 (27)

exp A B C D E F G
1 1 1 1 1 1 1 1
2 1 1 1 2 2 2 2
3 1 2 2 1 1 2 2
4 1 2 2 2 2 1 1
5 2 1 2 1 2 1 2
6 2 1 2 2 1 2 1
7 2 2 1 1 2 2 1
8 2 2 1 2 1 1 2
 Has a number of unique properties:
 Equal proportions of experiments
 Equal proportions of remaining factor levels
 Equal proportions of combinations of factor levels
 Is denoted as L 8 (27)
 Degree of freedom for factors =( number of levels
–1)
 Degree of freedom of OA: (Number of
experiment-1)
Interaction
 When the effect of one factor depends on the level of another
factor an interaction is said to exist

 An interaction occurs when the collective effect of two or


more factor taken together is different from the sum of each
of the factor taken individually

 If an interaction effect existed between factor A and B then


effect(A*B) would be confounded with the effect of factor C

 Confounded means that the effect of factor A and B would


be mixed up inseparably with that of factor C. We cannot
estimate the main effect due to C
Linear graph

 Represents factors and interaction assignments in


diagrammatic form
 A given orthogonal array can have several linear graph

1
*7
3 5 3 2
5
1 4
2 4
6
6 7
Interaction Table
Column Column

1 2 3 4 5 6 7
1 1 3 2 5 4 7 6
2 2 1 6 7 4 5
3 3 7 6 5 4
4 4 1 2 3
5 5 3 2
6 6 1
7 7
Assigning factors to an
orthogonal array
 Count the total degree of freedom needed for the
experiment based on the number of factors and
factor levels
 Select an OA that has at least the required number
of degree of freedom
 Draw the required linear graph
 Select an appropriate standard linear graph
 Assign each main effect and interaction to
appropriate column
Ina Sito Tile experiment
Ina sito Tile experiment
Factor Level 1 Level 2
A lime content A1 5% A2 1%
BGranularity B1 Coarse B2 fine
C Agalmatolite C1 43% C2 53%
D agalomatolite type D1 Current D2 Cheaper

E Charge quantity E1 1300 kg E2 1200kg

F waste return F1 0% F2 4%
G Felspar content G1 0% G2 5%
Result of experiment
exp A B C D E F G Resu
lt
1 1 1 1 1 1 1 1 16
2 1 1 1 2 2 2 2 17
3 1 2 2 1 1 2 2 12
4 1 2 2 2 2 1 1 6
5 2 1 2 1 2 1 2 6
6 2 1 2 2 1 2 1 68
7 2 2 1 1 2 2 1 42
8 2 2 1 2 1 1 2 26
Response Table
A B C D E F G

Level 1 12.7 26.7 25. 19 30.5 13.5 33


2
Level 2 35.5 21.5 23 29.2 17.7 34.7 15.2

Difference 22.2 5.2 2.2 10.2 12.7 21.2 17.7

Rank 1 6 7 5 4 2 3
Wind shield Washer Spray
Nozzle
 Problem: to improve the spray pattern and
reduce the velocity effect
 Obj.: For a given vehicle design, develop a
superior spray pattern and eliminate velocity
effect
 Factors and levels: Fore-aft position, side-to-
side position, number of orifices, orifice dia
with three and two levels
Factors
Trial 1(A) 2(B) 3(c) 4(d)
1 1 1 1 1
2 1 2 2 2
3 1 3 1 2
4 2 1 2 2
5 2 2 1 1
6 2 3 1 2
7 3 1 1 2
8 3 2 1 2
9 3 3 2 1
Popcorn experiment
 Statement of the problem
 Problem is to find the process factors which
influence popcorn quality characteristics
 The obj. is to find the process condition which
optimize the various quality characteristic to
provide improved popping, fluffiness
Measurement method
 The number of unpopped kernel in a batch
 The fluffiness can be quantified by placing
popped kernels in a measuring cup
 Popcorn process factors
 Assignment of factors to columns of
orthogonal array
 Conducting the popcorn experiment
 A batch of 200 seeds was used for each trial
with specified trial conditions.

You might also like