Title :
Neural networks as on-line approximators of nonlinear systems
Author :
Polycarpou, Marios M. ; Ioannou, Petros A.
Author_Institution :
Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
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
Keywords :
approximation theory; identification; neural nets; nonlinear systems; discrete-time dynamical systems; discrete-time formulation; identification; linearly parametrized networks; modeling; neural network; nonlinear systems; nonlinearly parametrized networks; online approximation; stability; Approximation methods; Artificial neural networks; Backpropagation algorithms; Ear; Feedforward neural networks; Mathematical model; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Power system modeling; Stability; Upper bound;
Conference_Titel :
Decision and Control, 1992., Proceedings of the 31st IEEE Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-0872-7
DOI :
10.1109/CDC.1992.371802
