What is Robust Design or Taguchi

1
What is Robust Design or Taguchis method?

• An experimental method to achieve product and
  process quality through designing in an
  insensitivity to noise based on statistical
  principles.

2
History of the method

• Dr. Taguchi in Japan 1949-NTT
• develops Quality Engineering
• 4 time winner of Demming Award
• Ford Supplier Institute, early 1980s
• American Supplier Institute, ASI
• Engineering Hall of Fame
• Statistics Community
• DOE
• S/N Ratio

3
Who uses Taguchis Methods

• Lucent
• Ford
• Kodak
• Xerox
• Whirlpool
• JPL
• ITT

• Toyota
• TRW
• Chrysler
• GTE
• John Deere
• Honeywell
• Black Decker

4
Documented Results from Use

• 96 improvement of NiCAD battery on satellites
  (JPL/ NASA)
• 10 size reduction, 80 development time
  reduction and 20 cost reduction in design of a
  choke for a microwave oven (L.G. Electronics)
• 50,000 annual cost savings in design of heat
  staking process (Ann Arbor Assembly Corp)
• 60 reduction in mean response time for computer
  system (Lucent)

• 900,000 annual savings in the production of
  sheet-molded compound parts (Chrysler)
• 1.2M annual savings due to reduction in vacuum
  line connector failures (Flex Technologies)
• 66 reduction in variability in arrival time and
  paper orientation (Xerox)
• 90 reduction in encapsulation variation (LSI
  Corp)

5
Insensitivity to Noise

• Noise Factors which the engineer can not or
  chooses not to control
• Unit-to-unit
• Manufacturing variations
• Aging
• Corrosion
• UV degradation
• wear
• Environmental
• human interface
• temperature
• humidity

6
How Noise Affects a System
7
Step 1 Define the Project Scope 1/2

• A gyrocopter design is to be published in a
  Sunday Comics section as a do-it-yourself project
  for 6-12 year old kids
• The customers (kids) want a product they can
  easily build and have a long flight time.

WW
--- WL --- BL ----
--- --- 1/4
8
Step 1 Define the Project Scope 2/2

• This is a difficult problem from an engineering
  standpoint because
• hard to get intuitive feel for effect of control
  variables
• cant control materials, manufacturing or assembly
• noise factors are numerous and have strong effect
  on flight.

9
Step 2 Identify Ideal Function

• Ideally want the most flight time (the quality
  characteristic or useful energy) for any input
  height (signal or input energy)
• Minimize Noise Effect
• Maximize Slope

Time of Flight
Drop Height
10
Step 3 Develop Noise Strategy 1/2

• Goal is to excite worst possible noise conditions
• Noise factors
• unit-to-unit
• aging
• environment

11
Step 3 Develop Noise Strategy 2/2

• Noise factors
• unit-to-unit
• Construction accuracy
• Paper weight and type
• angle of wings
• aging
• damage from handling
• environment
• angle of release
• humidity content of air
• wind

many, many others
12
Step 4 Establish Control Factors and Levels 1/4

• Want them independent to minimize interactions
• Dimensionless variable methods help
• Design of experiments help
• Confirm effect of interactions in Step 7
• Want to cover design space
• may have to guess initially and perform more than
  one set of experiments. Method will help
  determine where to go next.

13
Step 4 Establish Control Factors and Levels 2/4

• Methods to explore the design space
• shot-gun
• one-factor-at-a-time
• full factorial
• orthogonal array (a type of fractional factorial)

14
Step 4 Establish Control Factors and Levels 3/4
15
Step 4 Establish Control Factors and Levels 4/4
16
Step 5 Conduct Experiment and Collect Data
17
Data for Runs 5 and 15
18
Step 6 Conduct Data Analysis 1/7

• Calculate signal-to-noise-ratio (S/N) and Mean
• Complete and interpret response tables
• Perform two step optimization
• Reduce Variability (minimize the S/N ratio)
• Adjust the mean
• Make predictions about most robust configuration

19
Step 6 Conduct Data Analysis 2/7

• Calculate signal to noise ratio, S/N, a metric in
  decibels

variability S/N gain
reduction 3 27 6
50 12 75
Useful output Harmful output
S/N
Effect of Mean

Variability around mean
y2
10 log
Note This is one of many forms of S/N ratios.
s2
20
Step 6 Conduct Data Analysis 3/7
21
Step 6 Conduct Data Analysis 4/7Response Table
22
Step 6 Conduct Data Analysis 5/7Response plot
23
Step 6 Conduct Data Analysis 6/7Two Step
Optimization

• Reduce Variability (minimize the S/N ratio)
• look for control factor effects on S/N
• Dont worry about mean
• Adjust the mean
• To get desired response
• Use adjusting factors, those control factors
  which have minimal effect on S/N

24
Step 6 Conduct Data Analysis 7/7

• For gyrocopter
• wing width .75in
• wing length 2.00/0.75 2.67 in
• body length 2.00 x 2.67 5.33 in
• size 50
• no body folds
• no gussets

Predicted Performance S/N 9.44 dB Slope .31
sec/ft
25
Step 7 Conduct Conformation Run

• To check validity of results
• To check for unforeseen interaction effects
  between control factors
• To check for unaccounted for noise factors
• To check for experimental error

Predicted Confirmed S/N 9.44 dB
9.86 Slope .31sec/ft .32 sec/ft
26
How Taguchis Method Differs from an Ad-hoc
Design Process

• Organized Design Space Search
• Clear Critical Parameter Identification
• Focus on Parameter Variation (Noise)
• Clear Stopping Criteria
• Robustness centered not Failure Centered
• Reusable Method

• Concurrently Addresses Manufacturing Variation
• Concurrent Design-Test Not Design-Test-Fix
• Minimize Development Time (Stops Fire Fighting)
• Corporate Memory Through Documentation
• Encourages Technology Development Through System
  Understanding

27
How Taguchis Method Differs from Traditional
Design of Experiments

• Focused on reducing the impact of variability
  rather than reducing variability
• Focused on noise effects rather than control
  factor effects
• Clearly focused cost function - maximizing the
  useful energy

• Tries to reduce interaction between control
  factors rather than study them Requires little
  skill in statistics
• Usually lower cost

28
How Taguchis Method Differs from Shainins Method

• Focused on both Product and Process Design rather
  than Primarily on Process
• Oriented to developing a robust system not
  finding a problem (Red X). Taguchi tells what
  parameter values to set to make system
  insensitive to parameter Shainin identifies as
  needing control.

• Widely Used Internationally
• Fire prevention rather than fire fighting
• Accessible
• Many Case Studies Available

29
Plan for Application at Tektronix

• Select a parameter design problem
• Design the experiment
• Perform the experiment
• Reduce data
• Report results to Company
• Assuming success
• design more experiments
• train more engineers
• Plan for student-run experiments