A predictive control scheme based on neural networks

Purpose – To develop a new predictive control scheme based on neural networks for linear and non‐linear dynamical systems.Design/methodology/approach – The approach relies on three different multilayer neural networks using input‐output information with delays. One NN is used to identify the process under control, the other is used to predict the future values of the control error and finally the third one is used to compute the magnitude of the control input to be applied to the plant.Findings – This scheme has been tested by controlling discrete‐time SISO and MIMO processes already known in the control literature and the results have been compared with other control approaches with no predictive effects. Transient behavior of the new algorithm, as well as the steady state one, are observed and analyzed in each case studied. Also, online and offline neural network training are compared for the proposed scheme.Research limitations/implications – The theoretical proof of stability of the proposed scheme st...

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

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

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

[4]  Manuel A. Duarte,et al.  Control of grinding plants using predictive multivariable neural control , 2001 .

[5]  Yonghong Tan,et al.  Neural network based predictive control for nonlinear processes with time-delay , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[6]  Manfred Morari,et al.  Model predictive control: Theory and practice , 1988 .

[7]  Eric A. Wan,et al.  Temporal backpropagation for FIR neural networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[8]  Thomas J. McAvoy,et al.  Neural net based model predictive control , 1991 .

[9]  Robain De Keyser,et al.  Neural Networks Based Adaptive Predictive Control , 1994 .

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

[11]  B. Ydstie.  Forecasting and control using adaptive connectionist networks , 1990 .

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

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

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

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

[16]  John W. Eaton,et al.  Stability of neural net based model predictive control , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[17]  Robain De Keyser,et al.  Adaptive Neural Control for Processes with Large Deadtime , 1994 .

[18]  Manfred Morari,et al.  Model predictive control: Theory and practice - A survey , 1989, Autom..

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

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

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

[22]  Sigurd Skogestad,et al.  Limitations of dynamic matrix control , 1995 .