Continuous-time recurrent multilayer perceptrons for nonlinear system identification

In this paper continuous-time recurrent multilayer perceptrons (RMLP) are proposed to identify nonlinear systems. Using the function approximation theorem for multilayer perceptrons(MLP), we conclude that RMLP can approximate any dynamic system in any degree of accuracy. By means of a Lyapunov-like analysis, a stable learning algorithm for RMLP is determined. The suggested learning algorithm is similar to the well-known backpropagation rule of the multilayer perceptrons but with an additional term which assure the stability of identification error

[1]  E. Coddington,et al.  Theory of Ordinary Differential Equations , 1955 .

[2]  Manolis A. Christodoulou,et al.  Adaptive control of unknown plants using dynamical neural networks , 1994, IEEE Trans. Syst. Man Cybern..

[3]  Alexander S. Poznyak,et al.  Indirect adaptive control via parallel dynamic neural networks , 1999 .

[4]  J. Willems.  Least squares stationary optimal control and the algebraic Riccati equation , 1971 .

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

[6]  Frank L. Lewis,et al.  Robust neural-network control of rigid-link electrically driven robots , 1998, IEEE Trans. Neural Networks.

[7]  Alexander S. Poznyak,et al.  Nonlinear adaptive trajectory tracking using dynamic neural networks , 1999, IEEE Trans. Neural Networks.

[8]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Alexander S. Poznyak,et al.  Multilayer dynamic neural networks for non-linear system on-line identification , 2001 .

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

[11]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[12]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[13]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[14]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..