Pareto efficient correlated multi-response optimisation by considering customer satisfaction

Abstract

The capability of a manufacturer in satisfying the customer’s requirements is an important issue in the current competitive market. Since customers consider several correlated quality characteristics for selecting a product, designing the process variables to meet the required specification limits of the quality characteristics is essential. Furthermore, to attain the most satisfactory solution, a decision maker’s preference information should be incorporated into the optimisation procedure. This study suggests a posterior preference articulation approach based on NSGA-II and MOPSO, which is capable to increase customer satisfaction by generating non-dominated solutions within conformance region. The proposed method takes also into account the location and dispersion effects along with the correlation of among quality characteristics as well as the relative importance of them. To demonstrate the applicability of the approach, a computational analysis on two case studies is performed. Results confirm superiority of the suggested method in comparison with the existing posterior approaches.