Imprecise Knowledge in Expert Systems: A Simple Shell

摘要

Expert knowledge is often pervaded by imprecision and/or uncertainty, and this vagueness is considered more and more as a part of the expertise. Methods such as probability theory, error calculation, Bayesian approach or certainty factor have been used for a long time in order to deal with uncertainty or imprecision. Among these methods, fuzzy logic has the particularity to allow the management of uncertainty and imprecision in a unique framework. One of the interests of fuzzy logic in expert systems is that it handles in a single frame both imprecision and uncertainty, for instance through the generalized modus ponens approach. Shells allowing to implement this approach are usually quite heavy to handle and a simple shell that implements these concepts has been developed in order to provide students with a user-friendly and powerful environment. The main originality of this shell, called FLESH (Fuzzy Logic Expert Shell on Hypertext) is that it associates various semantics with the implications involved in the production rules. Furthermore, the simplicity of its interfaces has enabled the use the system for two years for educational purposes. Two expert systems developed with this shell are shortly described: a decision support system for production activity control and an expert system, for ball-bearing selection and assembly.