An Efficient Way to Optimizing Multiple Quality Characteristics in Quality Management: Posterior Preference Articulation Method

Response Surface Methodology (RSM) is a major research field of quality management, which studies the relationship between a response (quality characteristic) and a number of input variables. In real-world RSM application problems, it is quite common that several responses are of interest. In this case, determination of optimum conditions on the input variables would require simultaneous consideration of all the responses. This is called a Multiple Response Surface (MRS) problem. One of the most important issues in MRS Optimization is how to obtain a satisfactory ?compromise? solution considering a Decision Maker (DM)?s preference information on the tradeoffs among multiple responses. A promising alternative to incorporate the DM?s preference information well into the problem is the posterior preference articulation approach, which first generates all (or most) of the nondominated solutions and then makes the DM select the best one from the set of nondominated solutions a posteriori. This paper proposes a new posterior method to MRSO, which does not generate all the nondominated solutions before the selection stage, unlike other posterior methods which go on straightforward from generation to selection only once. Instead, it generates only the required nondominated solutions while making the response space of interest narrower gradually. The proposed method can improve the efficiency by minimizing the number of nondominated solutions generated.