Nonlinear adaptive control using neural networks and multiple models
- 1 January 2000
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6 (07431619) , 4199-4203 vol.6
- https://doi.org/10.1109/acc.2000.877012
Abstract
The principal contribution described here is concerned with combining linear and nonlinear models to improve the performance of essentially nonlinear dynamical systems even while assuring their stability. The system under consideration is defined, and some preliminaries about neural networks and growth rates of signals are given, which is central to the proof of stability. Following this, the well-known results in robust linear adaptive control are reproduced for easy reference. The key result of stability analysis when multiple models are used is presented. This is a very general result, and the special case when some of the models are actually neural networks is included.Keywords
This publication has 6 references indexed in Scilit:
- Adaptive control of discrete-time systems using multiple modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Adaptive bounding techniques for stable neural control systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Issues in the application of neural networks for tracking based on inverse controlIEEE Transactions on Automatic Control, 1999
- Adaptive control using multiple modelsIEEE Transactions on Automatic Control, 1997
- Multilayer discrete-time neural-net controller with guaranteed performanceIEEE Transactions on Neural Networks, 1996
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989