Neural networks as on-line approximators of nonlinear systems

The authors present an approximation theory perspective in the design and analysis of nonlinear system identification schemes using neural network and other online approximation models. The identification procedure considered is based on a discrete-time formulation. Depending on the location of the adjustable parameters, networks are classified into linearly and nonlinearly parametrized networks. Based on this classification, a unified procedure for modeling discrete-time dynamical systems using online approximators is developed. The proposed identification methodology guarantees stability of the overall system even in the presence of modeling errors, and upper bounds for the average output error are obtained in terms of the modeling error. Simulation studies are used to illustrate the results and to compare different approximation models.<<ETX>>

[1]  R. Bellman,et al.  V. Adaptive Control Processes , 1964 .

[2]  Stephen A. Billings,et al.  Identi cation of nonlinear systems-A survey , 1980 .

[3]  M. Powell,et al.  Approximation theory and methods , 1984 .

[4]  L. Schumaker.  Spline Functions: Basic Theory , 1981 .

[5]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[6]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[7]  Graham C. Goodwin,et al.  A parameter estimation perspective of continuous time model reference adaptive control , 1987, Autom..

[8]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

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

[10]  Karl Johan Åström,et al.  Adaptive Control , 1989, Embedded Digital Control with Microcontrollers.

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

[12]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[13]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[14]  R. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991 .

[15]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[16]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[17]  Petros A. Ioannou,et al.  Robust adaptive control: a unified approach , 1991 .

[18]  B. Kosko.  Fuzzy systems as universal approximators , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[19]  Robert Gardner,et al.  Introduction To Real Analysis , 1994 .