Multi-stage modelling of a semi-batch polymerization reactor using artificial neural networks

Three different approaches far modelling a semi-batch polymerization reacto r using artificial neural networks (ANN) have been investigated. Based on t he characteristics of the semi-batch reactor a multi-stage strategy is reco mmended. It divides the whole reaction process into two periods, semi-batch and batch, and further divides the semi-batch part into two sub-periods th at are before and after the maximum temperature is reached. Different ANN a rchitectures are used to model the three parts separately. The results demo nstrate that the multi-stage approach proposed can be used to estimate diff icult-to-measure polymer variables with acceptable accuracy for semi-batch processes. Concentrations of the monomer and the initiator in the reactor a re estimated from reactor temperature, feed temperature and the concentrati on of the initiator in the feed.