Modeling and Optimization of a Roll-Type Electrostatic Separation Process Using Artificial Neural Networks

The aim of this paper is the development of a procedure for the optimization of electrostatic separation processes using artificial neural networks (ANNs) in association with genetic algorithms. The objective was to maximize the insulation product, the control variables being the high voltage that supplies the electrode system and the rotation speed of the roll electrode. The ANN model is compared with that obtained using the classical experimental design methodology. The predicted optimum is confirmed by experiment.