Comparing Convergence of PSO and SFLA Optimization Algorithms in Tuning Parameters of Fuzzy Logic Controller

The paper presents using the Particle Swarm Optimization (PSO) and Shuffled Frog Leaping Algorithm (SFLA) to optimally tune parameters of a fuzzy logic controller stabilizing a rotary inverted pendulum system at its upright equilibrium position. Both the PSO and SFLA are meta-heuristic search methods. PSO is inspired by bird flocking behavior searching for food while SFLA is inspired from the memetic evolution of a group of frogs when seeking for food. In this study, the rule base of the Fuzzy Logic Controller (FLC) is brought by expert experience, and the parameters of the controller, i.e. the membership function parameters and scaling gains, are optimally tuned by the PSO and SFLA such that a predefined criterion is minimized. Simulation results show that the designed fuzzy controller is able to balance the rotary inverted pendulum system around its equilibrium state. Besides, convergent rate of SFLA is faster than that of PSO.