CONTROLLING INDUSTRIAL-PROCESSES THROUGH SUPERVISED, FEEDFORWARD NEURAL NETWORKS

Multi-layer, feedforward perceptron neural networks produce hetero- and auto- pattern associators which can be applied to a wide range of problems. The area of process monitoring and control is one of numerous inputs and outputs, which are normally non-determinative and do not adhere to known probability distributions. By training neural networks through supervised learning, such as backpropagation, a mechanized tool can be created which offers advantages over traditional methods based on statistics. Significant benefits are the ability to discern complex relationships and trends rather than assuming distributions (usually Gaussian) or specifying algorithms, the ability to integrate in real time large amounts of continuous data and adapt incrementally to changes in process, and the ability to handle noisy or incomplete data. This paper will examine multi-layered perceptrons trained by backpropagation, and why they are especially applicable to process control. The mathematics of the networks will be examined and compared to traditional parametric and non-parametric methods. Previous research and applications relating to process monitoring and control in an industrial setting will be discussed. Original research applying this technique to a PVC pipe manufacturer will be presented. Finally the limitations of the approach, and the outlook for neural networks as components of composite process control systems will be examined.