Application of evolutionary algorithm in optimizing the fuzzy rule base for nonlinear system modeling and control

Fuzzy systems generally work based on expert knowledge base. Fuzzy expert knowledge base incorporates human knowledge through fuzzy rules and fuzzy membership functions. In designing fuzzy models, a major difficulty in the identification of an optimized fuzzy rules as well as membership function shape and type of an individual rule. In fact, it is difficult and time consuming for an expert to define a complete rule set for a complex system having a large number of parameters. In this paper, we proposed a flexible encoding method for evolutionary algorithm to discover parameters of fuzzy rule, design of a suitable fuzzy models and controller for a particular environment. In Evolutionary Fuzzy System (EFS), evolutionary algorithms are adapted for finding the optimal fuzzy rule sets including the number of rules inside it and selecting the membership function shape and type of each individual rule in two different ways respectively. The benefits of this methodology are illustrated for the modeling and control of nonlinear system that shows better performance than existing fuzzy expert systems.