Extracting knowledge for product form design by using multiobjective optimisation and rough sets

Abstract

Industrial product form design has become consumer-centred. Affective responses related to consumers' affective needs are considered invaluable for product form design and have attracted increasing attention. When designing product forms, designers should thoroughly understand the design knowledge concerning multiple affective responses and design variables. This paper proposes a systematic approach to extraction of design knowledge by using multiobjective optimisation and rough sets. Design analysis is first employed to determine design variables and multiple affective responses. As per the results, a multiobjective optimisation model is constructed that involves optimising the multiple affective responses. An improved version of the strength Pareto evolutionary algorithm (SPEA2) is adopted to solve the multiobjective optimisation model and generate the Pareto optimal solutions. Based on these Pareto optimal solutions, rough sets are employed to extract design knowledge that is common to these Pareto optimal solutions. A car profile design was employed as a case study to illustrate the proposed approach. The results suggest that the proposed approach is time- and cost-efficient and can effectively extract design knowledge that provides suitable insight into product form design.