Applied Statistics and Probability for Engineers

14-2 SOME APPLICATIONS OF EXPERIMENTAL

DESIGN TECHNIQUES (CD ONLY)

Experimental design is an extremely important tool for engineers and scientists who are inter-

ested in improving the performance of a manufacturing process. It also has extensive application

in the development of new processes and in new product design. We now give some examples.

A Process Characterization Experiment

A team of development engineers is working on a new process for soldering electronic com-

ponents to printed circuit boards. Specifically, the team is working with a new type of flow

solder machine that should reduce the number of defective solder joints. (A flow solder

machine preheats printed circuit boards and then moves them into contact with a wave of

liquid solder. This machine makes all the electrical and most of the mechanical connections

of the components to the printed circuit board. Solder defects require touchup or rework,

which adds cost and often damages the boards.) The process will have several (perhaps

many) variables, and all of them are not equally important. The initial list of candidate vari-

ables to be included in the experiment is constructed by combining the knowledge and

information about the process from all team members. In this example, the engineers con-

ducted a brainstormingsession and invited manufacturing personnel with experience using

various types of flow soldering equipment to participate. The team determined that the flow

solder machine has several variables that can be controlled. They are

1. Solder temperature


2. Preheat temperature


3. Conveyor speed


4. Flux type


5. Flux-specific gravity


6. Solder wave depth


7. Conveyor angle
   In addition to these controllable factors, there are several other factors that cannot be easily
   controlled, once the machine enters routine manufacturing, including


8. Thickness of the printed circuit board


9. Types of components used on the board


10. Layout of the components on the board


11. Operator


12. Environmental factors


13. Production rate
    Sometimes we call the uncontrollable factors noisefactors. A schematic representation of
    the process is shown in Fig. S14-1.
    In this situation the engineer is interested in characterizingthe flow solder machine; that
    is, he is interested in determining which factors (both controllable and uncontrollable) affect
    the occurrence of defects on the printed circuit boards. To determine these factors, he can
    design an experiment that will enable him to estimate the magnitude and direction of the fac-
    tor effects. Sometimes we call such an experiment a screening experiment.The information
    from this characterization study or screening experiment can help determine the critical
    process variables, as well as the direction of adjustment for these factors in order to reduce the

14-1

PQ220 6234F.CD(14) 5/9/02 8:39 PM Page 1 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L: