中国物理B ›› 2012, Vol. 21 ›› Issue (10): 100205-100205.doi: 10.1088/1674-1056/21/10/100205

• GENERAL • 上一篇    下一篇

State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters

S. Lakshmanana, Ju H. Parka, H. Y. Junga, P. Balasubramaniamb   

  1. a Department of Information and Communication Engineering/Electrical Engineering, Yeungnam University, 214-1 Dae-Dong, Kyongsan 712-749, Republic of Korea;
    b Department of Mathematics, Gandhigram Rural Institute-Deemed University, Gandhigram-624 302, Tamilnadu, India
  • 收稿日期:2012-02-16 修回日期:2012-04-12 出版日期:2012-09-01 发布日期:2012-09-01
  • 基金资助:
    Project supported by the 2010 Yeungnam University Research Grant.

State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters

S. Lakshmanana, Ju H. Parka, H. Y. Junga, P. Balasubramaniamb   

  1. a Department of Information and Communication Engineering/Electrical Engineering, Yeungnam University, 214-1 Dae-Dong, Kyongsan 712-749, Republic of Korea;
    b Department of Mathematics, Gandhigram Rural Institute-Deemed University, Gandhigram-624 302, Tamilnadu, India
  • Received:2012-02-16 Revised:2012-04-12 Online:2012-09-01 Published:2012-09-01
  • Contact: Ju H. Park, H. Y. Jung E-mail:jessie@ynu.ac.kr; hoyoul@yu.ac.kr
  • Supported by:
    Project supported by the 2010 Yeungnam University Research Grant.

摘要: This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed time-varying delays and Markovian jumping parameters. The addressed neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov process. By construction of a suitable Lyapunov-Krasovskii functional, a delay-dependent condition is developed to estimate the neuron states through available output measurements such that the estimation error system is globally asymptotically stable in a mean square. The criterion is formulated in terms of a set of linear matrix inequalities (LMIs), which can be checked efficiently by use of some standard numerical packages.

关键词: neural networks, state estimation, neutral delay, Markovian jumping parameters

Abstract: This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed time-varying delays and Markovian jumping parameters. The addressed neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov process. By construction of a suitable Lyapunov-Krasovskii functional, a delay-dependent condition is developed to estimate the neuron states through available output measurements such that the estimation error system is globally asymptotically stable in a mean square. The criterion is formulated in terms of a set of linear matrix inequalities (LMIs), which can be checked efficiently by use of some standard numerical packages.

Key words: neural networks, state estimation, neutral delay, Markovian jumping parameters

中图分类号:  (Delay and functional equations)

  • 02.30.Ks
05.45.Gg (Control of chaos, applications of chaos)