AN EXPERT-SYSTEM BASED APPROACH TO MANUFACTURING CELL DESIGN

The design of cellular systems is a complex, multi-criteria and multi- step process which can have significant implications for the entire or ganization. Most research in this area focuses on the formation of par t families and associated machine groups, one step in the cell design process. Numerous quantitative techniques have been developed to addre ss this part-family/machine group formation problem. Existing approach es include math programming, algorithms for matrix diagonalization, th e application of network modelling and the use of similarity coefficie nts. These mathematically-oriented techniques can handle a relatively limited set of quantitative objectives and, in addition, require many simplifying assumptions. For this reason, the solutions generated by t hese techniques are of limited usefulness in actual cell design. This paper proposes an expert system approach to cell system design. The st arting point for the expert system is the initial solution generated b y traditional mathematical techniques. Based on a flexible set of user -driven quantitative and qualitative factors, the expert system evalua tes these preliminary solutions for feasibility and quality. If the so lutions are not satisfactory (infeasible or of low quality), the syste m suggests modifications.