Control of nonisothermal CSTR with time varying parameters via dynamic neural network control (DNNC)

Dynamic neural network control (DNNC) is a model predictive control strateg y potentially applicable to nonlinear systems. It uses a neural network to model the process and its mathematical inverse to control the process. The advantages of single hidden layer DNNC are threefold: First, the neural net work structure is very simple, having limited nodes in the hidden layer and output layer for the SISO case. Second, DNNC offers potential for better i nitialization of weights along with fewer weights and bias terms. Third, th e controller design and implementation are easier than control strategies s uch as conventional and hybrid neural networks without loss in performance. The objective of this paper is to present the basic concept of single hidd en layer DNNC and illustrate its potential. In addition, this paper provide s a detailed case study in which DNNC is applied to the nonisothermal CSTR with time varying parameters including activation energy (i.e., deactivatio n of catalyst) and heat transfer coefficient (i.e., fouling). DNNC is compa red with PID control. Although it is clear that DNNC will perform better th an PID, it is useful to compare PID with DNNC to illustrate the extreme ran ge of the nonlinearity of the process. This paper represents a preliminary effort to design a simplified neural network-based control approach for a c lass of nonlinear processes. Therefore, additional work is required for inv estigation of the effectiveness of this approach for other chemical process es such as batch reactors. The results show excellent DNNC performance in t he region where conventional PID control fails. (C) 2000 Elsevier Science S .A. All rights reserved.