GA Based Optimization of Hybrid Fuzzy PID Controller Systems

摘要

This paper introduces a new approach towards optimal design of a hybrid proportional- integral plus derivative (PID) controller applicable for controlling linear as well as nonlinear system using Genetic Algorithm The fuzzy PID Controller is a discrete time version of conventional PID Controller, which preserves same linear structure of Proportional, Integral and Derivative parts but has constant coefficient yet self tuned gains. Contrary to many existing fuzzy PID Controllers which require different fuzzy control spaces for different systems, the proposed approach allows the designer to use only one well defined linear fuzzy control space with fixed structure parameters for both linear and nonlinear system The constant PID gains are optimized using a Multi Objective Genetic Optimization there by yielding an optimal fuzzy controller. Computer simulations are shown to demonstrate its improvement over Fuzzy PID Controller without Multi Objective Genetic Optimization.