Direct adaptive output tracking control using multilayered neural networks

Multilayered neural networks are used to construct nonlinear learning control systems for a class of unknown nonlinear systems in a canonical form. An adaptive output tracking architecture is proposed using the outputs of the two three-layered neutral networks which are trained to approximate the unknown nonlinear plant to any desired degree of accuracy by using the modified back-propagation technique. A weight-learning algorithm is presented using the gradient descent method with a dead-zone function, and the descent and convergence of the error index during weight learning are shown. The closed-loop system is proved to be stable, with the output tracking error converging to the neighbourhood of the origin. The effectiveness of the proposed control scheme is illustrated through simulations.

[1]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[2]  Edward K. Blum,et al.  Approximation theory and feedforward networks , 1991, Neural Networks.

[3]  S Mangrulkar,et al.  Artificial neural systems. , 1990, ISA transactions.

[4]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[5]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[6]  Allon Guez,et al.  ART based adaptive pole placement for neurocontrollers , 1991, Neural Networks.

[7]  Stefen Hui,et al.  Analysis of Single Perceptrons Learning Capabilities , 1991, 1991 American Control Conference.

[8]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.

[9]  M.M. Gupta,et al.  Adaptive Tracking of SISO Nonlinear Systems Using Multilayered Neural Networks , 1992, 1992 American Control Conference.

[10]  Jean-Jacques E. Slotine,et al.  Sliding controller design for non-linear systems , 1984 .

[11]  J. J. Slotine,et al.  Tracking control of non-linear systems using sliding surfaces with application to robot manipulators , 1983, 1983 American Control Conference.

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

[13]  Fu-Chuang Chen,et al.  Adaptive Control of Nonlinear Systems Using Neural Networks - A Dead-Zone Approach , 1991, 1991 American Control Conference.

[14]  G. R. Walsh,et al.  Methods Of Optimization , 1976 .