Design of an Industrial Process Controller using Neural Networks

There are many problems in industrial process control systems due to a long system response delay, dead-zone and/or saturation of the actuator mechanisms, uncertainties in the system model and/or parameters, and process noise. To overcome these problems, an adaptive controller is designed using neural networks and tested extensively via simulations. One of the key problems in designing such a controller is to develop an efficient training algorithm. Neural networks are usually trained using the output errors of the network, instead of using the output errors of the controlled plant. However, when a neural network is used to control a plant directly, the output errors of the network are unknown, since the desired control actions are unknown. In this paper, we propose a simple training algorithm for a class of nonlinear systems, which enables the neural network to be trained by the output errors of the controlled plant. The only a priori knowledge of the controlled plant is the direction of its output response. A detailed analysis of the algorithm is presented and the corresponding theorems are proved. Due to its simple structure and algorithm, and good performance, the proposed controller has high potential for handling difficult problems in industrial process control systems.