USE OF NEURAL NETWORKS FOR MODELING OF OLEFIN POLYMERIZATION IN HIGH-PRESSURE TUBULAR REACTORS

Neural network computing is one of the fastest growing fields of artif icial intelligence due to its ability to ''learn'' nonlinear relations hips. This article presents the approach of back propagation neural ne tworks for modeling of free radical polymerization in high pressure tu bular reactors. Industrial data were used to train the network for pre diction of the temperature profile along the reactor, as well as polym er properties such as density, melt flow index, and molecular weight a verages. Comparisons were made between the neural network and mechanis tic model predictions published in the literature. Results showed the promising capability of a neural network as an alternative approach to model polymeric systems. (C) 1994 John Wiley & Sons, Inc.