SIMULTANEOUS DESIGN OF MEMBERSHIP FUNCTIONS AND RULE SETS FOR FUZZY CONTROLLERS USING GENETIC ALGORITHMS

This paper examines the applicability of genetic algorithms (GA's) in the simultaneous design of membership functions and rule sets for fuzz y logic controllers. Previous work using genetic algorithms has focuse d on the development of rule sets or high performance membership funct ions; however, the interdependence between these two components sugges ts a simultaneous design procedure would be a more appropriate methodo logy. When GA's have been used to develop both, it has been done seria lly, e.g., design the membership functions and then use them in the de sign of the rule set. This, however, means that the membership functio ns were optimized for the initial rule set and not the rule set design ed subsequently. GA's are fully capable of creating complete fuzzy con trollers given the equations of motion of the system, eliminating the need for human input in the design loop. This new method has been appl ied to two problems, a cart controller and a truck controller. Beyond the development of these controllers, we also examine the design of a robust controller for the cart problem and its ability to overcome fau lty rules.