Stability Analysis of Nonlinear System Identification via Delayed Neural Networks
- 20 February 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 54 (2) , 161-165
Abstract
In this brief, the identification problem for time-delay nonlinear system is discussed. We use a delayed dynamic neural network to do on-line identification. This neural network has dynamic series-parallel structure. The stability conditions of on-line identification are derived by Lyapunov-Krasovskii approach, which are described by linear matrix inequality. The conditions for passivity, asymptotic stability and uniform stability are established in some senses. We conclude that the gradient algorithm for updating the weights of the delayed neural networks is stable to any bounded uncertaintiesKeywords
This publication has 17 references indexed in Scilit:
- Novel global asymptotic stability criteria for delayed cellular neural networksIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 2005
- New results for exponential stability of delayed cellular neural networksIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 2005
- Global stability of a class of neural networks with time-varying delayIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 2005
- Absolute periodicity and absolute stability of delayed neural networksIEEE Transactions on Circuits and Systems I: Regular Papers, 2002
- LMI-based approach for asymptotically stability analysis of delayed neural networksIEEE Transactions on Circuits and Systems I: Regular Papers, 2002
- Some new results on system identification with dynamic neural networksIEEE Transactions on Neural Networks, 2001
- On the passivity of linear delay systemsIEEE Transactions on Automatic Control, 2001
- Global stability analysis of bidirectional associative memory neural networks with time delayInternational Journal of Circuit Theory and Applications, 2001
- NL/sub q/ theory: checking and imposing stability of recurrent neural networks for nonlinear modelingIEEE Transactions on Signal Processing, 1997
- Stability of analog neural networks with delayPhysical Review A, 1989