Chapter 4 - Hybrid nature-inspired algorithms for the optimal tuning of fuzzy controllers

Abstract

This chapter first describes the hybridization of particle swarm optimization (PSO) and gravitational search algorithms (GSAs) and later introduces a gray wolf optimization (GWO) using PSO's search mechanism. The operating algorithm of a hybrid PSOGSA and GWOPSO are presented. Combining two nature-inspired algorithms is necessary in order to reduce one's search process drawbacks by using the other's fortes. In the case of the PSOGSA, the PSO's exploitation capabilities and GSA's exploration abilities are combined to avoid getting trapped in local minima situations, while in GWOPSO's case, the exploitation advantages of PSO are employed in order to speed the GWO's convergence. The hybrid algorithms are inserted in the design approach dedicated to the optimal tuning of simple Takagi-Sugeno proportional-integral fuzzy controllers for the position control of servo systems. Four optimization problems are solved and some results concerning the hybrid PSOGSA's behavior are presented.