271
Some Guidelines for Designing an Industrial Expcriment
Table 1. Steps in Experimentation
1. Recognition of and statement of the problem
2. 1Choice of factors and Ievels
3. 1Selection of the response variable(s)
4. Choice of experimental design
5. Conduction of the experiment
6. Data analysis
7. Conclusions and recommendations
In some situations, steps 2 and 3 can be reversed, or they may be done simultaneously.
The objective of the first experiment then might be variable screening, to be followed by subsequent experiments that have as their objective determining the appropriate operating region for the process, optimization of the process, or determining process robustness.
It is important to fully develop all ideas about the objectives of the experiment. This means obtaining input from all concemed parties: engineering, quality assurance, manufacturing, marketing, management, the customer, and operating personnel (who usually have much insight and who are too often ignored). A elear statement of the problem often contributes substantially to a better understanding of the phenomena and the finał solution of the problem. This argues strongly for a team approach to designing experiments. Furthermore, the team members should agree on objectives, agree on the criteria that determine when the objectives have been attained, and communicate about all important issues such as a change in the objectives.
Coleman and Montgomery (1993) stress that objectives should be unbiased, specific, measurable, and of practical consequence. The team approach to experimental design encourages unbiased objectives. To be specific and measurable, the objectiyes should be detailed and stated so that it is elear when they have been met. In formulating objectives, it is important to evaluate all that is currently known including previous experimental results, observational data, information about relevant Chemical or physical laws, and expert scientific/engineering opinion.