Transcript DFSS
DESIGN FOR SIX SIGMA & ROBUST DESIGN OF PRODUCTS AND PROCESSES FOR QUALITY
Gülser Köksal EM507 METU, Ankara 2009
OUTLINE
• • • • • DFSS – DMAIC vs. DFSS – Different DFSS roadmaps – DMADV Roadmap – How To implement DFSS Robust design examples A review of design of experiments and orthogonal arrays Taguchi’s robust design approach – Loss Fuunctions – Signal-to-Noise Ratios Robust design case study: Cookie recipe design
Slides 3-16 are selected from the following presentation:
To design new products or processes, or to improve the designs of existing ones in order to satisfy customer requirements
DFSS – DMAIC
To improve the existing processes in order to satisfy customer requirements.
Six Sigma
Process Management
To achieve the business results, managing the processes efficiently.
Define Measure Analyze Improve Control
DMAIC
Define the problem with outputs and potential inputs Analyze the existing process: Is the process measured correctly? If so, what is the capability of the process?
Analyze and identify the important factors that cause the variation of the process: Where and when do the defects occur?
Optimize the output by optimizing the inputs: To reach at the six sigma process, what should be the levels of each factor?
Which controls should be done in order to continue process at six sigma?
Improvement Strategies
Customer Requirements Process Capability DMAIC DFSS NO Is the gap small?
Fundamental Redesign
• Design a new product / process • Broad approach • Blank sheet of paper approach • High risk • Longer time span • Addressing many CTQs • Goal: Quantum Leap
YES Iterative Improvement
• Fix an existing process • Narrow Focus • Use current process model • Low risk • Shorter Time Span • Addressing few CTQs • Goal: Improvement
When to Go for DFSS
Changing customer expectations: by the time the current problems are solved, new problems will occur Technology development: new technologies allow to meet all customer requirements at lower cost or gain a competitive edge Next generation: the existing products remaining lifetime is very short, a successor will be needed soon System limits: the performance gap is due to system / business model configurations that cannot be changed or the available technology does not allow to meet CTQs Process entirely broken: the existing process is unable to meet many CTQs, too many successive DMAIC projects required
Influence on cost, cycle time and quality
MANUFACTURING TRANSACTION %20-30 DESIGN %70-80 DESIGN MANU.-TRAN.
Different DFSS Methodologies
Several roadmaps have been proposed. They are very similar to each other. The underlying tools are the same
DFSS Methodology: DMADV
D efine
the project goals and customer requirements.
M easure
and determine customer needs and specifications; benchmark competitors and industry.
A nalyze
the process options to meet the customer needs.
D esign
(detailed) the process to meet the customer needs.
V erify
the design performance and ability to meet customer needs.
DFSS Methodology: DCCDI
D efine
the project goals.
C ustomer
analysis.
C oncept
ideas are developed, reviewed and selected.
D esign
is performed to meet the customer and business specifications.
I mplementation
is completed to develop and commercialize the product/service.
DFSS Methodology: IDOV
I dentify
the customer and specifications (CTQs).
D esign
translates the customer CTQs into functional requirements and into solution alternatives.
O ptimize
uses advanced statistical tools and modeling to predict and optimize the design and performance.
V alidate
makes sure that the design developed will meet the customer CTQs.
DFSS Methodology: DMADV
D efine
the project goals, customer requirements, and opportunities
M easure
in detail customer needs and priorities, market conditions, and benchmark competitors
A nalyze
the data collected, prioritize CTQs, determine relations between CTQs and parts/processes
D evelop
concept, innovative solutions, and optimal solutions to product and process design
V alidate
the solutions and implement
DFSS Methodology: DMADV
DEFINE MEASURE ANALYZE DEVELOP VALIDATE TOOLS Project management QFD Benchmarking Value analysis Financial analysis SIPOC IPDS FMEA TRIZ Design scorecards MSA Basic statistical techniques DOE Optimization Simulation Robust design Tolerance design Reliability engineering Design for manufacture and assembly
All methodologies are similar
Define the project goals, customer requirements , and opportunitie s Define Measure in detail customer needs and priorities, market conditions, and benchmark competitors Measure Analyze the data collected, prioritize CTQs, determine relations between CTQs and parts/processe s Analyze Develop concept, innovative solutions, and optimal solutions to product and process design Develop Validate the solutions and implement Validate Identify Design Optimize Verify
How is it implemented?
2 weeks of DFSS training Six Sigma BB or GB knowledge required for participation 2 project groups and 1 project per group In between training and after training there are a lot of MBB coachings (2-3 days/project-month)
Six Sigma Black Belt BB Week 1 BB Week 2 BB Week 3 BB Week 4 Design For Six Sigma DFSS Week 1 DFSS Week 2 Six Sigma Green Belt GB Week 1 GB Week 2
Or combined Six Sigma / DFSS Black Belt training program Totally 5 weeks of training Black Belts work on the design project Team members may participate on a common project
Robust Design Problem
To make system outputs insensitive to variation in inputs, process and environmental factors.
X 1 X 2 X 3 X 4 X 5 X 6 Product or Process Y 1 Y 2 Y 3 Outputs Inputs (Control Factors) W 1 W 2 W 3 Noise Factors (uncontrollable)
Robust Product Design Example
Making system output robust to environmental usage conditions
Sugar Flour Egg Milk Oil Baking powder Making a cake using a cake mix Taste Texture Inputs Oven type Altitude from sea level Customer requirements (controllable) Noise factors (uncontrollable)
A robust cake mix recipe reduces variability in taste and texture.
Robust Product Design Example
Making system output robust to component variability Utilizing the second degree relationship between system output and inputs What should be the pendulum length to minimize variation in the period?
Pendulum length
Robust Process Design Example
Making system robust to process variability Steam %20 %10 %30 S 2 S 1 What should be the amount of steam blown and amount of water sprayed into the closed system to generate a level of 20% humidity?
Guidelines for Robust Design through Statistical Experimentation
1. Choose control factors and their levels 2. Identify uncontrollable (noise) factors and decide on how they will be simulated 3. Select the response variable(s) and determine the performance measures (mean, standard deviation, SNR, etc.) 4. Setup the experimental layout (choose appropriate design array(s)) 5. Conduct the experiments and collect data 6. Analyze the data (effects, ANOVA, regression) 7. Choose optimal control factor levels and predict the performance measure at these levels 8. Confirm the optimal levels by experimentation
Ortogonal Array
L 4 L 8 L 9 L 12 L 16 L 16 L 18 L 25 L 27 L 32 L 32 L 36 L 36 L 50 L 54 L 64 L 64 L 81
No. of rows
4 8 9 12 16 16 18 25 27 32 32 36 36 50 54 64 64 81
Orthogonal Arrays
Max. no. of factors
3 7 4 11 15 5 8 6 13 31 10 23 16 12 26 63 21 40
Max. no. of factors at these levels 2
3 7 11 15 1 31 1 11 3 1 1 63 -
3
4 7 13 12 13 25 40
4
9 5 21 -
5
6 11 -
Ortogonal Array Construction Example
One factor with 2 levels, 6 factors with 3 levels
Quality (Consumer) Loss
The quality of a product is measured by estimating “the total loss to the customers due to variation in the product’s functions. For ideal quality, loss is zero. Higher the loss, lower the quality.
(b) (b) (b) LSL
Quality Loss Average Quality Loss
µ=T USL
Quality characteristic (X)
= b (x-T)
2
= b (
2
+( -T)
2
) (Taguchi,1989) Loss coefficient
Smaller-the-Better Response
• Loss Function L(Y) L(y) y L ( y ) A 2 y 2 L A 2 ( y 2 s 2 ) • Signal to Noise Ratio:
SNR
10
log(
1
n i n
1
y i
2
)
10
log( y
2
s
2
)
Examples: • Gas, Energy etc. consumption • Noise • Radiation
Larger-the-Better Response
• Loss Function L(Y) L(y) y
L
(
y
)
A
2 1
y
2
L
A
2 1
y
2 ( 1 3
s
2
y
2 ) Examples: • Mechanical power • Strength • Wearout resistance • Signal to Noise Ratio:
SNR
10 log( 1
n i n
1 1
y i
2 ) 10 log( 1
y
2 ( 1
s
2 3
y
2 ))
Nominal-the-Best Response
• Loss Function L(Y) L(y) y
L
(
y
)
A
2
L
A
2 (
s
2 (
y
(
y T
) 2
T
) 2 ) Examples: • Dimension (mm) • Strength • Voltage (V) • Signal to Noise Ratio:
1. Minimize variance
SNR
10 log
s
2
2. Bring the mean to the target
SNR
10 log(
n y
2 )
A Robust Design Experiment Layout
i 1 2 3 1 1 1 Control Factors 1 2 3 1 2 3 1 2 3 y 11 y 21 y 31 y 12 y 22 y 32 Noise Factors ………....
………....
………....
………....
………....
………....
………....
y 1n y 2n y 3n Performance Measures y 1 , s 1 2 , SNR 1 y 2 , s 2 2 , SNR 2 m 3 3 2 1 y m1 y m2 ………....
y mn y m , s 2 m , SNR m
Cookie Recipe Robust Design (A larger the-better robust design problem)
Objective:
To find the control factor levels that maximize cookie chewiness under uncontrollable effects of the noise factors.
Control Factors: A
: Cooking temperature
B
: Syrup content
C
: cooking time
D
: cooking pan
E
: Shortening type
Noise Factors:
Z1: Cookie position Z2: Temperature at test
Levels:
Low, high Low, high Short, long Solid, mesh Corn, coconut
Levels:
Side, middle Low, high (Source: W.J. Kolarik, 1995, Creating Quality, McGraw-Hill)
The experimental design layout, and data collected
Chewiness measurements
Z1
: side side middle middle
Z2
: low high low high
s
y 1 3
i
4 1 (
y i
y
) 2 log e s SNR 10 log( 1 4 i 4 1 1 y i 2 )
Response Tables
A*B A*C A*E B*C B*D B*E C*D C*E D*E
Taguchi Analysis: y1; y2; y3; y4 versus A; B; C; D; E
The following terms cannot be estimated, and were removed.
Response Table for Signal to Noise Ratios Larger is better Level A B C D E 1 22,18 12,69 17,40 16,03 16,74 2 15,70 25,19 20,48 21,85 21,13 Delta 6,49 12,50 3,08 5,82 4,39 Rank 2 1 5 3 4 Response Table for Means Level A B C D E 1 20,250 8,750 12,750 13,750 16,250 2 14,000 25,500 21,500 20,500 18,000 Delta 6,250 16,750 8,750 6,750 1,750 Rank 4 1 2 3 5 Response Table for Standard Deviations Level A B C D E 1 4,774 5,437 5,756 6,132 6,665 2 7,781 7,117 6,798 6,422 5,889 Delta 3,007 1,680 1,042 0,289 0,776 Rank 1 2 3 5 4
Marginal Average (Main Effect) Plots
Main Effects Plot (data means) for SN ratios
A B C 24 21 18 15 12 1 2 D 24 21 18 15 12 1 2 Signal-to-noise: Larger is better 1 1 E 2 2 1 2 Variables A, B, D and E have significant effects on SNR. C does not seem to be significant. But let us check this with ANOVA as well.
Interaction Plots
Interaction Plot (data means) for SN ratios
1 2
A
24 21 18 15 12 A 1 2 24 21 18 15 12 1 Signal-to-noise: Larger is better 2
D
D 1 2 Only AD interaction could be estimated and it seems to be insignificant.
ANOVA for SNR
Analysis of Variance for SN ratios Source DF Seq SS Adj SS Adj MS F P A 1 84,126 84,126 84,126 28,18 0,034 B 1 312,689 312,689 312,689 104,74 0,009 C 1 18,981 18,981 18,981 6,36 0,128 D 1 67,643 67,643 67,643 22,66 0,041 E 1 38,553 38,553 38,553 12,91 0,069 Residual Error 2 5,970 5,970 2,985 Total 7 527,962
Stat choose
DOE
Taguchi
Analyze Taguchi Design-Analysis ‘fit linear model for Signal to Noise ratios’
Predict Results at the Optimal Levels
Stat
DOE
Taguchi
Predict Taguchi Results
Predict Results at the Optimal Levels
Taguchi Analysis: y1; y2; y3; y4 versus A; B; C; D; E Predicted values
S/N Ratio Mean StDev Log(StDev) 35,0761 37,25 5,89143 1,83763 Factor levels for predictions A B C D E 1 2 2 2 2 Conduct confirmation experiments at these levels!
(
SNR
)
T
(
A
1
T
) (
B
2
T
) (
C
2
T
) (
D
2
T
) (
E
2
T
)