Particle Swarm Optimization Based Adaptive Strategy for Tuning of Fuzzy Logic Controller

Abstract

This paper presents a new method for learning and tuning a fuzzy logic controller automatically by means of a particle swarm optimization (PSO). The proposed self-learning fuzzy logic control that uses the PSO with adaptive abilities can learn the fuzzy conclusion tables, their corresponding membership functions and fitness value where the optimization only considers certain points of the membership functions. To exhibit the effectiveness of proposed algorithm, it is used to optimize the Gaussian membership functions of the fuzzy model of a nonlinear problem. Moreover, in order to design an effective adaptive fuzzy logic controller, an on line adaptive PSO based mechanism is presented to determine the parameters of the fuzzy mechanisms. Simulation results on two nonlinear problems are derived to demonstrate the powerful PSO learning algorithm and the proposed method is able to find good controllers better than neural controller and conventional controller for the target problem, cart pole type inverted pendulum system.