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

被引：55

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 50 条

[1] Novel results on robust finite-time passivity for discrete-time delayed neural networks
Mathiyalagan, K.
Park, Ju H.
Sakthivel, R.
[J]. NEUROCOMPUTING, 2016, 177 : 585 - 593
[2] Robust stability and passivity analysis for discrete-time neural networks with mixed time-varying delays via a new summation inequality
Thipcha, Jenjira
Tangsiridamrong, Presarin
Botmart, Thongchai
Meesuptong, Boonyachat
Ali, M. Syed
Srisilp, Pantiwa
Mukdasai, Kanit
[J]. AIMS MATHEMATICS, 2023, 8 (02): : 4973 - 5006
[3] Improved Stability Criteria for Discrete-time Delay Systems via Novel Summation Inequalities
Xiao, Shenping
Xu, Linxing
Zeng, Hong-Bing
Teo, Kok Lay
[J]. INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2018, 16 (04) : 1592 - 1602
[4] Improved Stability Criteria for Discrete-time Delay Systems via Novel Summation Inequalities
Shenping Xiao
Linxing Xu
Hong-Bing Zeng
Kok Lay Teo
[J]. International Journal of Control, Automation and Systems, 2018, 16 : 1592 - 1602
[5] Finite-time passivity of discrete Markov jump neural networks
Yang Lele
Chen Yun
Qiu Houming
[J]. PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 1966 - 1971
[6] New Results on Passivity Analysis of Delayed Discrete-Time Stochastic Neural Networks
Yu, Jianjiang
[J]. DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2009, 2009
[7] New finite-time passivity criteria for delayed fractional-order neural networks based on Lyapunov function approach
Shafiya, M.
Nagamani, G.
[J]. CHAOS SOLITONS & FRACTALS, 2022, 158
[8] Finite-time stability for discrete-time systems with time-varying delay and nonlinear perturbations by weighted inequalities
Shi, Chenyang
Vong, Seakweng
[J]. JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2020, 357 (01): : 294 - 313
[9] On H∞ Finite-Time Boundedness and Finite-Time Stability for Discrete-Time Neural Networks with Leakage Time-Varying Delay
Tuan, Le A.
[J]. NEURAL PROCESSING LETTERS, 2024, 56 (01)
[10] Existence of Solutions and Finite-Time Stability for Nonlinear Singular Discrete-Time Neural Networks
Le A. Tuan
Vu N. Phat
[J]. Bulletin of the Malaysian Mathematical Sciences Society, 2019, 42 : 2423 - 2442

← 1 2 3 4 5 →