Evolutionary Optimization of Robust and Chattering-Free Mamdani Type Fuzzy Controller

Abstract

In fuzzy control area, the evolutionary algorithm is one of the most common design tools for fuzzy knowledge base generation. In this paper, we present the application of an integer evolutionary algorithm (IEA) for simultaneous optimization of fuzzy rule base and fuzzy data base of Mamdani-type fuzzy controller. The motivation behind this work is to design a robust and accurate controller without chattering phenomenon in the control input. More specifically, we consider the minimization of the variance of the control input in the same time as root mean square tracking error during the optimization. This fact leads the IEA to search for accurate fuzzy controller that provides just enough control input for smooth behavior. To assess the design technique, simulations were conducted with direct-drive DC motor. The simulation results show the effectiveness of the proposed IEA in designing a robust and chattering-free Mamdani fuzzy controller with high accuracy as compared to a conventional PD controller