中国物理B ›› 2011, Vol. 20 ›› Issue (8): 80201-080201.doi: 10.1088/1674-1056/20/8/080201

• GENERAL •    下一篇

Robust stability analysis of Takagi–Sugeno uncertain stochastic fuzzy recurrent neural networks with mixed time-varying delays

M. Syed Ali   

  1. Department of Mathematics, Thiruvalluvar University, Vellore-632 106, Tamilnadu, India
  • 收稿日期:2011-01-05 修回日期:2011-01-05 出版日期:2011-08-15 发布日期:2011-08-15

Robust stability analysis of Takagi–Sugeno uncertain stochastic fuzzy recurrent neural networks with mixed time-varying delays

M. Syed Ali   

  1. Department of Mathematics, Thiruvalluvar University, Vellore-632 106, Tamilnadu, India
  • Received:2011-01-05 Revised:2011-01-05 Online:2011-08-15 Published:2011-08-15

摘要: In this paper, the global stability of Takagi—Sugeno (TS) uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays (TSUSFRNNs) is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSUSFRNNs. The proposed stability conditions are demonstrated through numerical examples. Furthermore, the supplementary requirement that the time derivative of time-varying delays must be smaller than one is removed. Comparison results are demonstrated to show that the proposed method is more able to guarantee the widest stability region than the other methods available in the existing literature.

Abstract: In this paper, the global stability of Takagi—Sugeno (TS) uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays (TSUSFRNNs) is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSUSFRNNs. The proposed stability conditions are demonstrated through numerical examples. Furthermore, the supplementary requirement that the time derivative of time-varying delays must be smaller than one is removed. Comparison results are demonstrated to show that the proposed method is more able to guarantee the widest stability region than the other methods available in the existing literature.

Key words: recurrent neural networks, linear matrix inequality, Lyapunov stability, time-varying delays, TS fuzzy model

中图分类号:  (Delay and functional equations)

  • 02.30.Ks
02.30.Sa (Functional analysis) 02.60.Cb (Numerical simulation; solution of equations) 02.40.Vh (Global analysis and analysis on manifolds)