IDENTIFICATION AND OPTIMIZING CONTROL OF A ROUGHER FLOTATION CIRCUIT USING AN ADAPTABLE HYBRID-NEURAL MODEL

In this paper the identification and control of a rougher flotation pr ocess is studied using an adaptable hybrid-neural model. The model is based on first principles and a PCA neural network is used for flotati on kinetics estimation. Initially, the hybrid model is used for the id entification, from input/output data obtained with a realistic phenome nological model, of a series of four flotation cells. Then, different regulatory and optimizing multivariable control alternatives are devel oped and tested on the process. The control problem is adaptively solv ed as an optimization problem, using predictions for the steady state obtained using the hybrid model. Results obtained for different input perturbations, setpoint changes and optimization tests show satisfacto ry performance, satisfying all required objectives without off-set or oscillation. Based on these results, the hybrid model can be considere d an excellent option for the identification and control of flotation plants, from the point of view of flexibility and robustness. (C) 1997 Published by Elsevier Science Ltd.