Observer design for switched recurrent neural networks: An average dwell time approach

Download

Full text for this resource is not available from the Research Repository.

Export

Lian, Jie, Feng, Zhi and Shi, Peng (2011) Observer design for switched recurrent neural networks: An average dwell time approach. IEEE Transactions on Neural Networks, 22 (10). pp. 1547-1556. ISSN 1045-9227

Abstract

This paper is concerned with the problem of observer design for switched recurrent neural networks with time-varying delay. The attention is focused on designing the fullorder observers that guarantee the global exponential stability of the error dynamic system. Based on the average dwell time approach and the free-weighting matrix technique, delaydependent sufficient conditions are developed for the solvability of such problem and formulated as linear matrix inequalities. The error-state decay estimate is also given. Then, the stability analysis problem for the switched recurrent neural networks can be covered as a special case of our results. Finally, four illustrative examples are provided to demonstrate the effectiveness and the superiority of the proposed methods.

Dimensions Badge

Altmetric Badge

Item type	Article
URI	https://vuir.vu.edu.au/id/eprint/10320
DOI	10.1109/TNN.2011.2162111
Official URL	http://dx.doi.org/10.1109/TNN.2011.2162111
Subjects	Historical > Faculty/School/Research Centre/Department > Institute for Logistics and Supply Chain Management (ILSCM) Historical > FOR Classification > 0801 Artificial Intelligence and Image Processing Historical > SEO Classification > 970118 Expanding Knowledge in Law and Legal Studies
Keywords	ResPubID24784, Average dwell time method, exponential stability, observer design, switched neural networks, time-varying delay
Citations in Scopus	101 - View on Scopus
Download/View statistics	View download statistics for this item