Adaptive Neuro Fuzzy Inference System PID Controller for AVR System Using SNR-PSO Optimization

Abstract

This paper presents an intelligent Proportional Integral Derivative (PID) controller for Automatic Voltage Regulator (AVR) system using Adaptive Neuro Fuzzy Inference System (ANFIS). In the proposed method, the PID controller parameters are tuned off line by using combination of Signal to Noise Ratio (SNR) and Particle Swarm Optimization (PSO) algorithm to minimize the cost function over a wide range of operating condition. The optimal values of PID controller parameters obtained from SNR-PSO algorithm for each considered operating condition are used to train ANFIS. Therefore, the proposed techniques could online tune the PID controller parameters at any other operating condition to improve the transient response of the system. In order to evaluate the performance of the SNR-PSO PID controller, the results are compared with the Genetic Algorithm (GA). Also, the performance of proposed intelligent PID controller is compared with the robust SNR-PSO PID controller with fixed parameters. The comparison shows the SNR-PSO based ANFIS controller is more efficiency than robust PID controller.