Improved delay-dependent stability result for neural networks with time-varying delays

被引：37

作者：

Shao, Hanyong ^{[1
]}

Li, Huanhuan ^{[1
]}

Shao, Lin ^{[2
]}

机构：

[1] Qufu Normal Univ, Res Inst Automat, Rizhao 276826, Peoples R China

[2] Beijing Univ Posts & Telecommun, Sch Elect Engn, Beijing 100876, Peoples R China

来源：

ISA TRANSACTIONS | 2018年 / 80卷

基金：

中国国家自然科学基金;

关键词：

Neural networks; Lyapunov-Krasovskii functional; Integral inequality; Asymptotic stability; ASYMPTOTIC STABILITY; CRITERIA; STABILIZATION;

D O I：

10.1016/j.isatra.2018.05.016

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper is concerned with a new Lyapunov-Krasovskii functional (LKF) approach to the stability for neural networks with time-varying delays. The LKF has two features: First, it can make full use of the information of the activation function. Second, it employs the information of the maximal delayed state as well as the instant state and the delayed state. When estimating the derivative of the LKF we employ a new technique that has two characteristics: One is that Wirtinger-based integral inequality and an extended reciprocally convex inequality are jointly employed; the other is that the information of the activation function is used as much as we can. Based on Lyapunov stability theory, a new stability result is obtained. Finally, three examples are given to illustrate the stability result is less conservative than some recently reported ones.

引用

页码：35 / 42

页数：8

共 32 条

[1] An integral inequality in the stability problem of time-delay systems [J].

Gu, KQ .

PROCEEDINGS OF THE 39TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 2000, :2805-2810

[2] Novel stability criteria for recurrent neural networks with time-varying delay [J].

Ji, Meng-Di ;

He, Yong ;

Zhang, Chuan-Ke ;

Wu, Min .

NEUROCOMPUTING, 2014, 138 :383-391

[3] New and improved results on stability of static neural networks with interval time-varying delays [J].

Kwon, O. M. ;

Park, M. J. ;

Park, Ju H. ;

Lee, S. M. ;

Cha, E. J. .

APPLIED MATHEMATICS AND COMPUTATION, 2014, 239 :346-357

[4] Combined Convex Technique on Delay-Dependent Stability for Delayed Neural Networks [J].

Li, Tao ;

Wang, Ting ;

Song, Aiguo ;

Fei, Shumin .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2013, 24 (09) :1459-1466

[5] Delay-Slope-Dependent Stability Results of Recurrent Neural Networks [J].

Li, Tao ;

Zheng, Wei Xing ;

Lin, Chong .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (12) :2138-2143

[6] New approach to stability criteria for generalized neural networks with interval time-varying delays [J].

Liu, Yajuan ;

Lee, S. M. ;

Kwon, O. M. ;

Park, Ju H. .

NEUROCOMPUTING, 2015, 149 :1544-1551

[7]

Michel A.N., 2002, Qualitative Analysis and Synthesis of Recurrent Neural Networks

[8] Reciprocally convex approach to stability of systems with time-varying delays [J].

Park, PooGyeon ;

Ko, Jeong Wan ;

Jeong, Changki .

AUTOMATICA, 2011, 47 (01) :235-238

[9]

Samidurai R., 2016, IEEE T SYST MAN CYB, P1

[10] Wirtinger-based integral inequality: Application to time-delay systems [J].

Seuret, A. ;

Gouaisbaut, F. .

AUTOMATICA, 2013, 49 (09) :2860-2866

← 1 2 3 4 →