Design of a self tuning fuzzy PID controller by the accumulated genetic algorithm

Abstract

A self-tuning fuzzy PID (SFPID) controller is proposed in this paper. The structure of the proposed SFPID controller consists of both fuzzy PI-like controller and fuzzy PD-like controller. Both of fuzzy PI-like and PD-like controllers are weighted through self-tuning gains, which are also determined by fuzzy logic inference. A modified genetic algorithm called accumulated genetic algorithm is designed to learn the parameters of fuzzy inference system. In order to learn the number of fuzzy rules required for the TSK model, the fuzzy rules are learned in an accumulated way. In other words, the parameters learned in the previous rules are accumulated and updated along with the parameters in the current rule. It will be shown that the proposed SFPID controllers learned by the accumulated GA perform well for not only the regular linear systems but also the higher order and time-delayed systems.