Artificial neural networks for modelling and predictive control of an industrial evaporation process Original Research Article

Since the beginning of collaboration with the sugar industry in 1989, the objective has been the improvement of manufacturing processes to achieve optimal operating conditions. The present paper deals with the non-linear modelling of multiple-effect evaporation in the cane sugar industry, with the aim of robust control. To overcome the limits of the traditional control systems, a model-based predictive control (MPC) scheme was designed. As this control strategy requires the development of a predictive model, a multistep ahead predictor neural network (NN) model of the plant was used. The test of the identified NN models in generalisation, and the simulation of the MPC scheme, on the basis of experimental data collected during several measurement campaigns at the Bois Rouge sugar mill, illustrate the good performances of this new approach, showing promises for an on-line implementation in the year 2000.