In manufacturing experimental design techniques

In manufacturing, experimental design techniques applied early in process
design and development can result in
1. improved yield
2. reduced variability and closer conformance to nominal or desired
output

3. reduced development time
4. reduced overall costs
Guidelines for Designing Experiments
1. Identification of the problem and clear problem statements.
2. Scan and choice of factors and their levels
3. Deciding the output or response variable
4. Choice of experimental design
5. Performing the experiment
6. Data collection and analysis
7. Results, conclusions and recommendations (act on)
Steps 1 & 2 are pre-experimental planning. Steps 2 & 3 can be done
simultaneously, also in reverse order.
Experimental Approaches
1. One can combine factors arbitrarily, then test them and see the
results. This strategy is called best-guess approach . Need a great
technical and theoretical knowledge. Still trial-and-error approach.
Actually, no best results. Best is always cunning!
2. One-factor-at-a-time approach . Select a starting point (base line set
of levels) for each factor, and then change the level of one factor
keeping all others at base line levels. Do the test and report the
response. But, this method cannot locate interaction (of factors)
effect. Interactions between factors are quite common. Therefore,
such experiments are always less efficient than other statistical
methods.
Response
Low High
Factor x
1
Response
Low High
Factor x
2

Figure: One-factor-at-a-time approach (no interaction)
Table: Effects and data for one-factor-at-a-time experiment
TC Factors/levels Response
y
A B C D … H
1 1 1 1 1 … 1 y
0
(benchmark or ref.
value)
2 2 1 1 1 … 1 y
A
3 1 2 1 1 … 1 y
B
4 1 1 2 1 … 1 y
C
5 1 1 1 2 … 1 y
D
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
m 1 1 1 1 1 2 y
m
TC = treatment conditions; 1 = base level, 2 = changed level
Effects:
0
y y e
A A
 
(for changing from level 1 to level 2)
0
y y e
B B
 
, and so on. Which effect is largest and what is the
direction of any effect (+ve or – ve)?
Ex. Researchers are studying the effects of tire pressure, gas type, oil type,
and vehicle speed on gas mileage. What combination of factors provides
the best gas mileage? Data are:
Factors Level 1 Level 2 Response variable
Tire pressure 28 psi 35 psi Gas mileage
Speed 55 mph 65 mph
Oil 30 weight 40 weight
Gas Regular premium
TC Tire pressure
1
x
Speed
2
x
Oil
3
x
Gas
4
x
Mileage,
y
1 28 55 30 R
2 35 55 30 R
3 28 65 30 R
4 28 55 40 R

5 28 55 30 P
Complexity: trying to study all the different changes levels. No
interaction is allowed.
3. Factorial approach : The correct approach. Factors are varied
together . Simpler way is to set two levels of each factor. So for k
factors, number of experiments could be
k
2
. Experimenter can see
the main effects (effects of each factor separately) and interaction (a
result that generates when 2 or more factors are set together) effect.