A nonlinear PID controller for CSTR using local model networks

Abstract

The basic PID controllers have difficulty in dealing with problems that appear in complex nonlinear processes. This paper presents a practical nonlinear PID controller that deals with these nonlinear difficulties. It utilises a local model (LM) network, which combines a set of local models within an artificial neural network (ANN) structure, to adaptively characterise the process nonlinearity. Then a local controller network is formulated through a gating system deduced from the LMN to handle the nonlinearity. A continuous stirred tank reaction (CSTR) case study illustrates the practicality of this method in the modelling and control of nonlinear processes. PID controllers are still alive and appropriate for the control of nonlinear processes.