Stability analysis of neural networks with time-varying delay: Enhanced stability criteria and conservatism comparisons

被引：60
作者：
Lin, Wen-Juan [1 ,2 ]
He, Yong [1 ,2 ]
Zhang, Chuan-Ke [1 ,2 ]
Wu, Min [1 ,2 ]
机构：
[1] China Univ Geosci, Sch Automat, Wuhan 430074, Peoples R China
[2] Hubei Key Lab Adv Control & Intelligent Automat C, Wuhan 430074, Peoples R China
来源：
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION | 2018年 / 54卷
基金：
中国国家自然科学基金;
关键词：
Neural networks; Time-varying delay; Stability analysis; Relaxed integral inequality; Conservatism comparison; GLOBAL ASYMPTOTIC STABILITY; DEPENDENT STABILITY; EXPONENTIAL STABILITY; SYSTEMS;
D O I：
10.1016/j.cnsns.2017.05.021
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
This paper is concerned with the stability analysis of neural networks with a time-varying delay. To assess system stability accurately, the conservatism reduction of stability criteria has attracted many efforts, among which estimating integral terms as exact as possible is a key issue. At first, this paper develops a new relaxed integral inequality to reduce the estimation gap of popular Wirtinger-based inequality (WBI). Then, for showing the advantages of the proposed inequality over several existing inequalities that also improve the WBI, four stability criteria are derived through different inequalities and the same LyapunovKrasovskii functional (LKF), and the conservatism comparison of them is analyzed theoretically. Moreover, an improved criterion is established by combining the proposed inequality and an augmented LKF with delay-product-type terms. Finally, several numerical examples are used to demonstrate the advantages of the proposed method. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：118 / 135
页数：18
相关论文
共 51 条
[1]   Global asymptotic stability of neural networks with transmission delays [J].
Cao, JD .
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2000, 31 (10) :1313-1316
[2]   CELLULAR NEURAL NETWORKS - APPLICATIONS [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290
[3]   New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay Using Delay-Decomposition Approach [J].
Ge, Chao ;
Hua, Changchun ;
Guan, Xinping .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (07) :1378-1383
[4]   DELAY-INDEPENDENT STABILITY IN BIDIRECTIONAL ASSOCIATIVE MEMORY NETWORKS [J].
GOPALSAMY, K ;
HE, XZ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06) :998-1002
[5]  
Hampshire J B, 1990, IEEE Trans Neural Netw, V1, P216, DOI 10.1109/72.80233
[6]   Stability analysis for neural networks with time-varying interval delay [J].
He, Yong ;
Liu, G. P. ;
Rees, D. ;
Wu, Min .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (06) :1850-1854
[7]   New delay-dependent stability criteria for neural networks with time-varying delay [J].
He, Yong ;
Liu, Guoping ;
Rees, D. .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (01) :310-314
[8]   Delay-dependent exponential stability of delayed neural networks with time-varying delay [J].
He, Yong ;
Wu, Min ;
She, Jin-Hua .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2006, 53 (07) :553-557
[9]   Global exponential stability of neural networks with time-varying delay based on free-matrix-based integral inequality [J].
He, Yong ;
Ji, Meng-Di ;
Zhang, Chuan-Ke ;
Wu, Min .
NEURAL NETWORKS, 2016, 77 :80-86
[10]   Further results on exponential stability of neural networks with time-varying delay [J].
Ji, Meng-Di ;
He, Yong ;
Wu, Min ;
Zhang, Chuan-Ke .
APPLIED MATHEMATICS AND COMPUTATION, 2015, 256 :175-182
123456