Effect of Varying Controller Parameters on the Performance of a Fuzzy Logic Control System
This paper presents the results of computer simulation studies designed to isolate the effects of the major parameters of a fuzzy logic controller namely the range of the universe of discourse, the extent of overlap of the fuzzy sets, the rules in the rule base and the modes of the output fuzzy sets on the performance of a fuzzy logic control system. The controlled process was modeled by a nonlinear differential equation that was solved using the Runge-Kutta numerical method. The results show that varying the range of the universe of discourse of the inputs to the fuzzy controller affects both the transient response and the steady state error of the system, and that a desired system response could be achieved by adjusting the modes of the output fuzzy sets given a fairly good rule base. It has also been shown that the system response could be fine-tuned by varying the overlap of the input fuzzy sets.