Artificial neural network based multivariable predictive control

Considers the development of dynamic process models using artificial neural networks. Two alternative network modelling philosophies are considered; a time series approach and imbedded dynamics within the network structure. Both methods are shown to be suitable approaches to dynamic modelling, given due consideration to the methodologies of training. With process dynamics captured in the artificial neural network structural form, the model can be utilised within a conventional industrial multivariable long-range predictive control framework. Results are presented from the application of such a control scheme to a complex, non-linear distillation column simulation.<
>