Control of grinding plants using predictive multivariable neural control

This work investigates the use of a recently developed direct neural networ k (NN) multivariable predictive controller applied to a grinding plant. The NN controller is trained so that an estimation of the control error severa l steps ahead is minimized, which are given by a properly designed NN calle d predictor. An NN, which identifies the plant, is used to backpropagate th e control error at present instant of time, as well as at various steps ahe ad. A linear, as well as a phenomenological (nonlinear), model of CODELCO-A NDINA. grinding plant are used to simulate the proposed control strategy. T he linear model was built from empirical data obtained from a real grinding plant around an operating point. The phenomenological model is based on a mass balance and power consumption of the mills containing 17 particle size intervals. Several tests are performed, driving the process to an operatio n point, and then, controlling it by training the NN controller on line. Fi nally, a comparison with other control strategies already applied at a simu lation level is presented. These include classical and adaptive multivariab le control algorithms. All the results presented in the paper are based on simulations. (C) 2001 Elsevier Science B.V. All rights reserved.