Finite-Time Passivity-Based Stability Criteria for Delayed Discrete-Time Neural Networks via New Weighted Summation Inequalities

被引：57

作者：

Saravanakumar, Ramasamy ^{[1
,2
]}

Stojanovic, Sreten B. ^{[3
]}

Radosavljevic, Damnjan D. ^{[4
]}

Ahn, Choon Ki ^{[5
]}

Karimi, Hamid Reza ^{[6
]}

机构：

[1] Mahidol Univ, Dept Math, Fac Sci, Bangkok 10400, Thailand

[2] Kunsan Natl Univ, Res Ctr Wind Energy Syst, Gunsan Si 54005, South Korea

[3] Univ Nis, Fac Technol, Dept Engn Sci & Appl Math, Leskovac 16000, Serbia

[4] Univ Prishtina, Fac Sci & Math, Kosovska Mitrovica 38220, Serbia

[5] Korea Univ, Sch Elect Engn, Seoul 136701, South Korea

[6] Polytech Univ Milan, Dept Mech Engn, I-20156 Milan, Italy

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2019年 / 30卷 / 01期

基金：

新加坡国家研究基金会;

关键词：

Discrete-time neural networks (DNNs); finite-time passivity (FTP) analysis; Lyapunov method; weighted summation inequality; GLOBAL EXPONENTIAL STABILITY; SLIDING-MODE CONTROL; SYNCHRONIZATION; SYSTEMS;

D O I：

10.1109/TNNLS.2018.2829149

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we study the problem of finite-time stability and passivity criteria for discrete-time neural networks (DNNs) with variable delays. The main objective is how to effectively evaluate the finite-time passivity conditions for NNs. To achieve this, some new weighted summation inequalities are proposed for application to a finite-sum term appearing in the forward difference of a novel Lyapunov-Krasovskii functional, which helps to ensure that the considered delayed DNN is passive. The derived passivity criteria are presented in terms of linear matrix inequalities. A numerical example is given to illustrate the effectiveness of the proposed results.

引用

页码：58 / 71

页数：14

共 47 条

[1] Deadbeat Dissipative FIR Filtering [J].

Ahn, Choon Ki ;

Shi, Peng ;

Basin, Michael V. .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2016, 63 (08) :1210-1221

[2] Two-Dimensional Dissipative Control and Filtering for Roesser Model [J].

Ahn, Choon Ki ;

Shi, Peng ;

Basin, Michael V. .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2015, 60 (07) :1745-1759

[3]

[Anonymous], 2000, COMM CONT E

[4] Robust stochastic stability of discrete-time fuzzy Markovian jump neural networks [J].

Arunkumar, A. ;

Sakthivel, R. ;

Mathiyalagan, K. ;

Park, Ju H. .

ISA TRANSACTIONS, 2014, 53 (04) :1006-1014

[5] Finite-time stability analysis of discrete-time fuzzy Hopfield neural network [J].

Bai, Jianjun ;

Lu, Renquan ;

Xue, Anke ;

She, Qingshan ;

Shi, Zhonghua .

NEUROCOMPUTING, 2015, 159 :263-267

[6] Impulsive Stabilization and Impulsive Synchronization of Discrete-Time Delayed Neural Networks [J].

Chen, Wu-Hua ;

Lu, Xiaomei ;

Zheng, Wei Xing .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (04) :734-748

[7] Dynamic Output-Feedback Dissipative Control for T-S Fuzzy Systems With Time-Varying Input Delay and Output Constraints [J].

Choi, Hyun Duck ;

Ahn, Choon Ki ;

Shi, Peng ;

Wu, Ligang ;

Lim, Myo Taeg .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2017, 25 (03) :511-526

[8] Neural networks for system identification [J].

Chu, S.Reynold, 1600, (10)

[9] Passivity and complexity [J].

Chua, LO .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (01) :71-82

[10]

Debeljkovic DL, 2013, INT CONF SYST SCI EN, P177, DOI 10.1109/ICSSE.2013.6614655

← 1 2 3 4 5 →