A Method for Applying Neural Networks to Control of Nonlinear Systems

This chapter discusses a new method for applying neural networks to control of nonlinear systems. Contrast to a conventional method, the new method does not use neural network directly as a nonlinear controller or nonlinear prediction model, but use it indirectly via an ARX-like macro-model, in which neural network is embedded. The ARX-like model incorporating neural network is constructed in such a way that it has similar linear properties to a linear ARX model. The nonlinear controller is then designed in a similar way as designing a controller based on a linear ARX model. Numerical examples are used to illustrate the usefulness of the new method.

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

[2]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[3]  Venkataramanan Balakrishnan,et al.  System identification: theory for the user (second edition): Lennart Ljung; Prentice-Hall, Englewood Cliffs, NJ, 1999, ISBN 0-13-656695-2 , 2002, Autom..

[4]  Stephen A. Billings,et al.  International Journal of Control , 2004 .

[5]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[6]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[7]  David M. Burton,et al.  Introduction to Modern Abstract Algebra , 1967 .

[8]  Kotaro Hirasawa,et al.  A Hierarchical Method for Training Embedded Sigmoidal Neural Networks , 2001, ICANN.

[9]  Jun Wang,et al.  Recurrent neural networks for nonlinear output regulation , 2001, Autom..

[10]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[11]  Jinglu Hu,et al.  Quasi-ARMAX Modeling Approaches to Identification and Prediction of Nonlinear Systems , 2000 .

[12]  Hassan K. Khalil,et al.  Adaptive control of a class of nonlinear discrete-time systems using neural networks , 1995, IEEE Trans. Autom. Control..

[13]  Tor Arne Johansen,et al.  On Tikhonov regularization, bias and variance in nonlinear system identification , 1997, Autom..

[14]  Ignacio Requena,et al.  Are artificial neural networks black boxes? , 1997, IEEE Trans. Neural Networks.

[15]  L. Ljung,et al.  Overtraining, regularization and searching for a minimum, with application to neural networks , 1995 .

[16]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[17]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

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

[19]  Cheng-Liang Chen,et al.  Self-organizing neural control system design for dynamic processes , 1993 .

[20]  O. Nelles.  Nonlinear System Identification , 2001 .

[21]  Snehasis Mukhopadhyay,et al.  Adaptive control using neural networks and approximate models , 1997, IEEE Trans. Neural Networks.

[22]  K. Hirasawa,et al.  A Quasi-ARMAX approach to modelling of non-linear systems , 2001 .