Artificial neural network based control

In the chemical process industry although most systems possess non-linear characteristics, control algorithms are synthesised based upon linear approximations. In some process situations, however, the use of a non-linear control strategy may impart operational advantages. In this contribution a new formulation of a non-linear predictive controller is proposed. The algorithm follows a model based approach where the nominal model for control algorithm synthesis is an artificial neural network. This type of model structure can be considered generic in the sense that little prior knowledge of the process is required. Unlike other commonly used black box approaches, a neural network based process model has the potential to describe more concisely the behaviour of complex process dynamics. Results are presented from application of the artificial neural network based controller to an exothermic chemical reactor and binary distillation column.<>