Self-tuning PID control of liquid level system based on Fuzzy Wavelet Neural Network model

Abstract

In this paper two objectives are followed; one is to illustrate the capability of Fuzzy Wavelet Neural Network (FWNN) in modeling; and the other is to propose a self-tuning PID controller based on this model. The controller is constructed by a FWNN structure combined with a PID controller. Gradient descent algorithm is used to accomplish tuning rules. The proposed method is applied for a nonlinear system, which is a liquid level system. The capability of FWNN in the modeling of nonlinear system by a few rules and susceptibility of the proposed controller will be shown by simulation. The convergence analysis of the algorithm will be done using Lyapunov theorem. It will be shown that the proposed method would increase the speed of tracking while having very little steady state error which is due to the high accuracy of fuzzy wavelet neural network.