Michel Benne

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

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.

Mechanistic Model versus Artificial Neural Network Model of a Single-Cell PEMFC

Model-based controllers can significantly improve the performance of Proton Exchange Membrane Fuel Cell (PEMFC) systems. However, the complexity of these strategies constraints large scale implementation. In this work, with a view to reduce complexity without affecting performance, two different modeling approaches of a single-cell PEMFC are investigated. A mechanistic model, describing all internal phenomena in a single-cell, and an artificial neural network (ANN) model are tested. To perform this work, databases are measured on a pilot plant. The identification of the two models involves the optimization of the operating conditions in order to build rich databases. The two different models benefits and drawbacks are pointed out using statistical error criteria. Regarding model-based control approach, the computational time of these models is compared during the validation step.

Neural modelling and control of a crystal growth process in cane sugar industry

Abstract This paper describes the development of an original neural model-based control strategy to improve a low grad crystallization process through the crystal growth phase. The modelling, to control the growing phase, is one of our main objectives. Through the identification of a neural model of this non linear phase, a way to improve the process control is proposed. It consists in a linearization of the neural network model, used to extract the linear model and to update the controller parameters. Results obtained during present investigation carried out encouraging improvements.