Finite-time H-infinity state estimation for switched neural networks with time-varying delays

Ali M. S., Saravanan S., Arik S.

NEUROCOMPUTING, vol.207, pp.580-589, 2016 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 207
  • Publication Date: 2016
  • Doi Number: 10.1016/j.neucom.2016.05.037
  • Journal Name: NEUROCOMPUTING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.580-589
  • Istanbul University Affiliated: Yes


This study considers the problem of finite-time H-infinity state estimation for the switched neural networks with time varying delay, based oh the theories of the switched systems. Sufficient conditions for the switched neural networks to be finite time stable and finite time bounded are derived. These conditions are delay dependent and are given in. terms of linear matrix inequalities (LMIs). Average dwell time of switching signals is also given such that switched neural networks are finite-time stable or finite-time bounded. By resorting to the average dwell time approach and Lyapunov-Krasovskii functional technology, the H-infinity estimator design are developed in terms of solvability of a set of linear matrix inequalities. Finally, numerical examples are provided to illustrate the effectiveness of the theoretical results. (C) 2016 Elsevier B.V. All rights reserved.