Control of grinding plants using predictive multivariable neural control

This work investigates the use of a recently developed direct neural network (NN) multivariable predictive controller applied to a grinding plant. The NN controller is trained so that an estimation of the control error several steps ahead is minimized, which are given by a properly designed NN called predictor. An NN, which identifies the plant, is used to backpropagate the control error at present instant of time, as well as at various steps ahead. A linear, as well as a phenomenological (nonlinear), model of CODELCO-ANDINA grinding plant are used to simulate the proposed control strategy. The 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 operation point, and then, controlling it by training the NN controller on line. Finally, a comparison with other control strategies already applied at a simulation level is presented. These include classical and adaptive multivariable control algorithms. All the results presented in the paper are based on simulations.

[1]  Alejandro Castillo,et al.  Multivariable control of grinding plants: a comparative simulation study. , 2002, ISA transactions.

[2]  J. A. Meech,et al.  Expert systems for teaching and training in the mineral industry , 1990 .

[3]  I-Lung Chien,et al.  Consider IMC Tuning to Improve Controller Performance , 1990 .

[4]  Raj K. Rajamani,et al.  Optimal control of a ball mill grinding circuit—II. Feedback and optimal control , 1991 .

[5]  R. Murray-Smith,et al.  Neural networks for modelling and control of a non-linear dynamic system , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.

[6]  Lennart Ljung,et al.  Theory and Practice of Recursive Identification , 1983 .

[7]  Yaman Arkun,et al.  Nonlinear Predictive Control of a Semi Batch Polymerization Reactor by an Extended DMC , 1989 .

[8]  Manuel A. Duarte,et al.  Grinding operation optimization of the codelco-andina concentrator plant , 1998 .

[9]  David D. Brengel,et al.  Multistep nonlinear predictive controller , 1989 .

[10]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[11]  I. M. MacLeod,et al.  The Application of Multivariable Adaptive Control to an Industrial Run-Of-Mine Milling Process , 1991 .

[12]  John A. Meech,et al.  Development of a self-tuning fuzzy logic controller , 1993 .

[13]  C. R. Cutler,et al.  Dynamic matrix control¿A computer control algorithm , 1979 .

[14]  Lester Kershenbaum,et al.  An extended horizon feedback/feedforward self‐tuning controller , 1989 .

[15]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[16]  Perez Correa.  Implementation of feedforward and multivariable self-tuning controllers in chemical processes , 1987 .

[17]  Dale E. Seborg,et al.  Nonlinear Process Control , 1996 .

[18]  Sebastian Engell,et al.  Model Predictive Control Using Neural Networks [25 Years Ago] , 1995, IEEE Control Systems.

[19]  Joel MacMurray,et al.  Identification of a Packed Distillation Column for Control Via Artificial Neural Networks , 1993, 1993 American Control Conference.

[20]  R. A. Bearman,et al.  Application of fuzzy logic and neural network technologies in cone crusher control , 1995 .

[21]  Barbara Hayes-Roth,et al.  Intelligent Control , 1994, Artif. Intell..

[22]  Thomas F. Edgar,et al.  Adaptive control strategies for process control: A survey , 1986 .

[23]  Manuel A. Duarte,et al.  A comparative experimental study of five multivariable control strategies applied to a grinding plant , 1999 .

[24]  N. Munro.  Recent extensions to the inverse Nyquist array design method , 1985, 1985 24th IEEE Conference on Decision and Control.

[25]  Kumpati S. Narendra,et al.  Optimization of Dynamical Systems Containing Neural Networks , 1991 .

[26]  Heinz Unbehauen,et al.  Multirate nonlinear predictive control , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[27]  Markus A. Reuter,et al.  The application of neural nets in the metallurgical industry , 1994 .

[28]  R. Sargent,et al.  Theory and application of an extended horizon self‐tuning controller , 1985 .

[29]  Raj K. Rajamani,et al.  APPLICATION OF MODERN CONTROL THEORY TO MINERAL-PROCESSING OPERATIONS. , 1982 .

[30]  Rajnikant V. Patel,et al.  Multivariable System Theory and Design , 1981 .

[31]  Bernard P. A. Grandjean,et al.  NEURAL NETWORKS IN PROCESS CONTROL - A SURVEY , 1992 .

[32]  Duncan A. Mellichamp,et al.  A decoupling pole placement self‐tuning controller for a class of multivariable processes , 1986 .

[33]  Maciejowsk.  Multivariable Feedback Design , 1989 .

[34]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[35]  Y. Arkun,et al.  Nonlinear Predictive Control of a Semi Batch Polymerization Reactor by an Extended DMC , 1989, 1989 American Control Conference.

[36]  Carlos E. Garcia,et al.  Internal model control. A unifying review and some new results , 1982 .

[37]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.