Prediction of polymer quality in batch polymerisation reactors using neural networks

Neural networks are used to learn the relationship between batch recipes and the trajectories of polymer quality variables in batch polymerisation. Given a batch recipe, the trained neural networks can predict polymer quality variables during the course of polymerisation. A main factor affecting prediction accuracy is reactive impurities which commonly exist in industrial polymerisation reactors. The amount of reactive impurities can be estimated online during the initial stage of polymerisation using another neural network. Accurate predictions of polymer quality variables can then be obtained from the effective batch initial conditions. The technique can be used to design optimal batch recipes and to monitor polymerisation processes.