NEURO BASED MODEL REFERENCE ADAPTIVE CONTROL OF A CONICAL TANK LEVEL PROCESS

N.S. Bhuvaneswari, G. Uma, and T.R. Rangaswamy

Keywords

Nonlinear process, conical tank, conventional controller, neurocontroller, fuzzy controller, neuro based MRAC

Abstract

This paper deals with the adaptive control of a continuous time nonlinear system of conical tank level process using neural networks. An adaptive system based on MRAC technique is proposed and proved to be useful in adjusting the trained parameter of the neural network for approximating the non-linearity of the dynamical system and for the process parameter variations. A neuro model is also developed for this purpose. The weight adaptive laws are developed using an adaptive neural network. The tracking error, which is the difference between the neuro model and the plant output, converge to the required accuracy through the adaptive control algorithm derived by combining the inverse neural network and adaptive neural network. A lab scale experimental setup for the conical tank level process was fabricated. Experimental studies were carried out for conventional control, fuzzy control, neuro control, and adaptive neuro control. The performances of all the above schemes were investigated. The advantages of the proposed scheme, over other methods, were highlighted.

Important Links:



Go Back