Rule selection for knowledge-based product design

Knowledge-intensive and collaborative environment becomes more significant in the modern product development. To realize a true knowledge-based product design environment, however, the complexity of design constraint is still cumbersome issue to tackle. Typically, product design information comes from various sources and rapidly changes; design is evolutionary. Thus, a minimal set of rules is required to make an appropriate design decision. This paper aims to present a rule reduct based approach to select systematically minimal set of rules. Rough set theory synthesizes approximation of concepts, analyzes data by discovering patterns, and classifies into certain decision classes, which can be extracted from data by means of methods based on Boolean reasoning and discernibility. In this paper, this rule reduct based approach is compared with the absorption theorem based approach.