RBF model based predictive control for exothermic semi-batch polymerizations

This paper presents a neural network based model predictive control (MPC) strategy to control a strongly exothermic reaction with complicated nonlinear kinetics given by Chylla-Haase polymerization reactor, this kind of reactor requires a very precise temperature control to maintain product uniformity. A radial basis function (RBF) neural network is trained by the recursive least square (RLS) algorithm and is used to model parameter uncertainty in nonlinear dynamics of the Chylla-Haase reactor. The predictive control strategy based on the RBF neural is applied to achieve set-point tracking of the reactor output against disturbances. The result shows that the RBF based model predictive control gives reliable result in the presence of some disturbances and keeping the reactor temperature within a tight tolerance range around the specified reaction temperature.