Professional Documents
Culture Documents
Design: An Overview
Vijay Nair
Statistical Methods
for Quality and Reliability
1920s
1950s
1950s
1970s+80s
1980s
1980s
1985
1990+
Defense
Y = f (A, B, unknowns)
Y = f (A, B) + error
Empirical approximations
to f (A,B)
Want to know: Effect of input parameters? Is A important?
How to manipulate A and B to optimize E(Y)? How sensitive
is the optimum to changes in A and B and noises?
Where in the A-B region should we conduct reliability stress
tests? How to extrapolate reliability results to the design
conditions?
First-order approximation:
Second-order approximation
Six Sigma
Typical Black Belt Training
Week 1
Core Six Sigma
CE Matrix
Process Capability
Measurement System
Correlation
Project Management
Week 3
Full Factorial
2^k Factorials
Fractional Factorials
Planning Experiments
EVOP
Adv. Meas. Systems
Week 2
Review Capability
Multivariate Analysis
Topics in Statistics
Introduction to DOE
Single Factor
Experiments
Week 4
Advanced Multivariate
Multiple Regression
Response Surface
Control Plans
Control Systems
Quality Function Dep.
Sequential designs
Complex
Complex Data
Data Structure
Structure
Curves,
Curves, Spatial
Spatial Objects,
Objects,
Worn Bearing
350
300
250
200
150
Worn Gib
Excessive Snap
100
50
0
-50
120
140
160
180
200
220
240
Virtual/Computer Experiments
Signal Factors s
Product/Process
Output
Y = f (x, z, s)
Target = T
Noise Factors z
How?
Y = f( x; s; z )
Exploit interactions between control factors (x)
and noise factors (z) to find settings of x that
achieve robustness while also trying to get good
average performance.
If f(.) is known, this is a regular optimization
problem.
In practice, f(.) unknown, so use physical
experimentation.
Implementation
Product Array Design
Noise Array
Systematically varying noise factors
Various strategies
Design for Control Factors
Control Array
Highly fractional designs
Mixed levels
Complex aliasing
Very little focus
on CxC interactions
Product Array
Can estimate all
CXN interactions
Control Factors:
A cycle time, B mold temp, C cavity thickness,
D holding pressure, E injection speed,
F holding time, G gas size
Noise Factors:
M - % regrind, N - moisture content, O ambient temp.
Analysis
Half-normal plot of
Location Effects
Half-normal plot of
Dispersion Effects
Gear System
Response:
Output torque
Signal:
Input torque
Control Factors: Gear material
Number of teeth
Type of contact
Noise Factors:
Run-out
Type of lubrication
Aging
Window photolithography
4-fold reduction in process variance
2-fold reduction in processing time
Film photo-resist
Reduced drop-out rate by 50%
Circuit design
Wave soldering, optimum solder flux formulation
Router Bit Life Improvement
UNIX System Response Time Optimization
1986
@ Taguchis House
Impact on Industry
Taguchi Methods
for Implementing Parameter Design
PerMIA
Mathematical formulation of two-stage
optimization and development for various
problems and loss functions
(Leon et al. 1987)
Generalized SN-ratios
Transformations
(Box, 1988; Nair and Pregibon, 1986)
GLM
Dual Response
Transformations
Variance-stabilizing transformations with no dispersion
effects:
log-transformation
GLM
Joint Modeling of Location and Dispersion Effects
Components
Mean
Dispersion
Response Variable
Deviance
Mean
Variance Function
Gamma distribution
Link Function
Linear Predictor
Remarks
More generally,
Treat noise factors as fixed and absorb into structural model:
Y (x) = f (control factors) + g (noise factors) + h (CxN interactions) +
Estimate effects of control and noise
factors and CxN interactions
Noise = Temp
+1
Factor A
Other Areas
Dynamic problems
Functional response
Signal-response systems
Dynamic systems
Probabilistic optimization
Research
Considerable research to understand and improve on
Taguchis methods for design and analysis
More analysis than design
Future?