A modular fixture design system based on case-based reasoning

An intelligent modular fixture design system based on case-based reasoning (CBR) is proposed in this paper. Knowledge in CBR is represented in cases instead of rules. Descriptions of the CBR algorithm and its advantage over the rule-based expert system are introduced. Modification is a main operation in the CBR algorithm. Functional features are applied at this stage. Each component in a modular fixture is assigned a functional feature according its function. These components for which the functions are unsatisfactory are modified to fit the new problem. The modified case is stored in a knowledge base and becomes new knowledge. An illustrated example is presented. Two characteristics are expected of this modular fixture design system. First, the design system becomes more intelligent than the traditional CAD system; it participates in complete design work rather than just printing the design. Secondly, the system can learn from every consultation and become more experienced.