Launsby Consulting 2002 Fall Technical Conference October 17 2002

Launsby Consulting 2002

Fall Technical Conference

October 172002


Robert Launsby Co-author of three books on

experimental design Co-developer of DOE Wisdom software Trained several thousand folks in

industry on problem solving approaches Article “Straight Talk on DFSS”, SSFM

8/2002 www.launsby.com

Download of examples using toys


Agenda Model for change “Super Simulation” of air bag

deployment system Trebuchets, electromagnets,

antacid pills, catapults


Boston Survival Skills Statement: Accents are wonderful,

We all have them (we just don’t know it)

South Boston (Kennedy accent) Car, Harvard, Chelmsford, Factor, Shark Data, Pizza, Cuba, peninsula “Park the car in Harvard yard” Tuna, tuner


Niccolo Machiavelli “There is nothing more difficult to carry

out, nor more doubtful of success, nor more dangerous to handle than to initiate a new order of things. For the reformer has enemies in all those who profit by the old order, and only lukewarm defender by all those who could profit by the new order. This luke-warmness arises from the incredulity of mankind who do no truly believe in anything new until they have had actual experience with it.”


Change The application of simple

statistical tools to day-to-day activities represents a huge change for many businesses


Strategic Change Matrix Right Thing Wrong Thing

Done Well

Done Poorly

Stage 1

Stage 2

Stage 3Stage 4

Continue doing old right thing

Deny new reality

Folks need practice!

The world changes


Getting Folks Out of Stage 2 Into Stage 3 High contrast and confrontation One approach

Air bag simulation using “Super Sim” Student challenge (30 minutes)

Team exercise Select best settings (25 trials max) Define technology guide for each

response


Auto Air Bag System

Orifice diameter

Type of charge, amount of charge

Gas weight

Four factors


Auto Air Bag System (cont.)

Factor Range

Orifice diameter

0.08 to 0.14

Gas weight 12.0 to 14.5

Prop. Type 23b, 35b

Prop. Weight .85, 1.2



Time to first pressure

Time to 90 % max.

Max Pressure delivered



Time to 90 %8 9 10

Max Pressure

110 120 130

Time to First Pressure

2 3

Goal: Nominal values for all three responses



D(composite)

wt

orif

Response Surface**type(B)=23b,propwt(D)=1.00000

0.0860.0968

0.10760.1184

0.12920.14

12.8

13

13.2

13.4

13.6

13.8

0

0.2

0.4

0.6

0.8

1


Getting Folks Out of Stage 3 Into Stage 4 Trebuchet

More complex DOE, PLS techniques Electromagnets

DOE, ANOVA, regression Antacid pills

Variance reduction, simple DOE Catapults

Problem solving, control charts, MSA, simple DOE

M&M’s for attributes MSA, C-charts

Tools are great for starters, but don’t forget real applications


Trebuchet Real Trebuchets were weapons of mass

destruction in 12th century Used in TV show “Northern Exposure” to

launch piano Today: Used to toss Yugo’s, pumpkins,

etc, great amount of info on internet Interesting challenge for getting

students beyond simple Design of Experiments, PLS


Possible Trebuchet Factors

Potential factors of interest

Number of weights

Pivot point of arm

Release arm position

Sling length

Release bar position

Possible responses

Total distance

Height

Flight distance


Trebuchet (cont.)Distance

8Multiple R:

0.998703

0.9974080.995463

2.89396

Variable Coefficient Std Error 95% CI Tolerance T P(2 Tail)

Constant 156.875 1.02317 ± 2.84133 153.323 0Rel Bar -27.125 1.02317 ± 2.84133 1 -26.511 0S Length -12.375 1.02317 ± 2.84133 1 -12.095 0AB -26.875 1.02317 ± 2.84133 1 -26.266 0

Standard Error of Estimate:

Dependent Variable:Number Runs(N):

Squared Multiple R:Adjusted Squared Multiple R:

Model looks good!


Trebuchet (cont.)

2 3 4 5

Rel Bar

0

0.6

1.2

1.8

2.4

3S Length

Contour Plot

Distance

180

160

140

120

100

Prediction is 165

Actual value from trial was 194


Trebuchet (cont.) Eventually fit special cubic model

to obtain useful predictions for flight distance with previous factor ranges

Note: you can download details from my website


Electromagnets

Some possible factors

Diameter of wire

Number of turns

Amount of current

Type of core

Distance of gauss meter from core

Possible Responses

Gauss

Distance from coil to move compass needle


Electromagnets (cont.)

0

10

20

30

40

green(-)gold(+)wire(A)

1.5(-)3(+)voltage(B)

0(-) 1(+)dist(C)

10(-)20(+)turns(D)

Factors

Main Effects

field str


Electromagnets (cont.)

10 12 14 16 18 20turns

1.5

1.8

2.1

2.4

2.7

3

voltage

Contour Plot**wire(A)=green,dist(C)=0.000000

field str

12

14

16

18

20


Antacid pills

Factors: Water temp, amount of cola

Response:

Dissolve time

Experiment demonstrates interaction, non-linearity, and variance reduction

0

100

200

1(-) 1.5 2(+)water(A)

Factors

Scatter Plot

time


Antacid pills (cont.)

0

20

40

60

80

100

120

1(-) 1.5 2(+)

acid(-)

1(-) 1.5 2(+)

acid(+)

1(-) 1.5 2(+)

acid(0)

water(A)

Factors

Interactions

time

Interaction tested to be significant


Catapult Possible factors: pull back angle, “pin on

pole”, hook position, cup position, stop position, ball type, etc.

Possible responses: total distance, height, flight distance.

Positives: simple linear model provides useful predictions

Other uses: Control charts (older rubber band will demonstrate shift in mean), problem solving


Catapult (cont.)

20

44

68

92

116

140

150(-) 186(+)Angle(A)

-1(-) 1(+)Band(B)

-1(-) 1(+)Peg(C)

Factors

Main Effects

dist


Catapult (cont.)

0

100

200

150(-) 186(+)

Band(-)

150(-) 186(+)

Band(+)

Angle(A)150(-) 186(+)

Peg(-)

150(-) 186(+)

Peg(+)

Angle(A)-1(-) 1(+)

Peg(-)

-1(-) 1(+)

Peg(+)

Band(B)

Factors

Interactions

dist


Catapult (cont.)

150 157.2 164.4 171.6 178.8 186

Angle

-1

-0.6

-0.2

0.2

0.6

1

Band

Contour Plot**Peg(C)=-1.00000

dist

20

80

100

120

60

40


Paper Helicopter Numerous potential factors

including Wing length Wing width Number of weights Type of weight Paper weight Body length


Paper HelicopterDependent Variable: TimeNumber Runs(N): 36Multiple R: 0.99464Squared Multiple R: 0.989308Adjusted Squared Multiple R: 0.980304Standard Error of Estimate: 0.0733144Variable Coefficient Std Error P(2 Tail)Constant 1.65896 0.0399463 0Wing Width(A) 0.186528 0.0145436 0Wing Length(B) 0.420556 0.0157747 0Weight(C) -0.290972 0.0145436 0Body Length(D) -0.0811806 0.0131981 0Paper(E) -0.181181 0.0131981 0AB -0.00777778 0.0157747 0.628AC 0.0419444 0.0145436 0.009AD -0.0390972 0.0131981 0.008AE -0.0203472 0.0131981 0.14BC -0.0827778 0.0157747 0BD -0.05625 0.015873 0.002BE -0.04625 0.015873 0.009CD 0.0696528 0.0131981 0CE 0.0709028 0.0131981 0DE -0.011875 0.015873 0.464Wing Length**2 0.0766667 0.0473242 0.122


Paper Helicopter

D(Time)

Paper

Wing Length

Response Surface**Wing Width(A)=2.40000,Weight(C)=1.40000,Body Length(D)=12.0000

1

1.2

1.4

1.6

1.8

2

55.8

6.67.4

8.29

0

0.2

0.4

0.6

0.8

1


M&M’s Simple to use Simple to define defect Useful for attributes R&R study and C-

charts You can sample (eat) some of the

product


Summary Please visit my website to

download case studies and find listing of what is required for each experiment

www.launsby.com

Documents

Launsby Consulting 2002 Fall Technical Conference October 17 2002