H∞ state estimation of stochastic memristor-based neural networks with time-varying delays

被引:65
作者
Bao, Haibo [1 ]
Cao, Jinde [2 ,3 ]
Kurths, Juergen [4 ,5 ]
Alsaedi, Ahmed [6 ]
Ahmad, Bashir [6 ]
机构
[1] Southwest Univ, Sch Math & Stat, Chongqing 400715, Peoples R China
[2] Southeast Univ, Sch Math, Nanjing 210096, Jiangsu, Peoples R China
[3] King Abdulaziz Univ, Fac Sci, Dept Math, Jeddah 21589, Saudi Arabia
[4] Potsdam Inst Climate Impact Res, D-14415 Potsdam, Germany
[5] Humboldt Univ, Inst Phys, D-12489 Berlin, Germany
[6] King Abdulaziz Univ, Dept Math, Nonlinear Anal & Appl Math NAAM Res Grp, Jeddah 21589, Saudi Arabia
基金
中国国家自然科学基金;
关键词
H-infinity state estimation; Memristor-based neural networks; Filippov solution; Time-varying delays; EXPONENTIAL SYNCHRONIZATION; STABILITY ANALYSIS; DISTRIBUTED DELAYS; MIXED DELAYS; NEUTRAL-TYPE; DISCRETE; PASSIVITY; PASSIFICATION; STABILIZATION; BIFURCATION;
D O I
10.1016/j.neunet.2017.12.014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper addresses the problem of H-infinity state estimation for a class of stochastic memristor-based neural networks with time-varying delays. Under the framework of Filippov solution, the stochastic memristor-based neural networks are transformed into systems with interval parameters. The present paper is the first to investigate the H-infinity state estimation problem for continuous-time Ito-type stochastic memristor-based neural networks. By means of Lyapunov functionals and some stochastic technique, sufficient conditions are derived to ensure that the estimation error system is asymptotically stable in the mean square with a prescribed H-infinity performance. An explicit expression of the state estimator gain is given in terms of linear matrix inequalities (LMIs). Compared with other results, our results reduce control gain and control cost effectively. Finally, numerical simulations are provided to demonstrate the efficiency of the theoretical results. (c) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码:79 / 91
页数:13
相关论文
共 48 条
[1]   Delay-distribution-dependent state estimation for discrete-time stochastic neural networks with random delay [J].
Bao, Haibo ;
Cao, Jinde .
NEURAL NETWORKS, 2011, 24 (01) :19-28
[2]  
Boyd S., 1994, STUDIES APPL NUMERIA
[3]   Stability and Hopf bifurcation in a simplified BAM neural network with two time delays [J].
Cao, Jinde ;
Xiao, Min .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (02) :416-430
[4]   MEMRISTOR - MISSING CIRCUIT ELEMENT [J].
CHUA, LO .
IEEE TRANSACTIONS ON CIRCUIT THEORY, 1971, CT18 (05) :507-+
[5]   H∞ state estimation for memristive neural networks with time-varying delays: The discrete-time case [J].
Ding, Sanbo ;
Wang, Zhanshan ;
Wang, Jidong ;
Zhang, Huaguang .
NEURAL NETWORKS, 2016, 84 :47-56
[6]  
Filippov A. F., 1988, SOVIET SERIES MATH I
[7]   Passivity and Passification of Memristor-Based Recurrent Neural Networks With Time-Varying Delays [J].
Guo, Zhenyuan ;
Wang, Jun ;
Yan, Zheng .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (11) :2099-2109
[8]   Attractivity Analysis of Memristor-Based Cellular Neural Networks With Time-Varying Delays [J].
Guo, Zhenyuan ;
Wang, Jun ;
Yan, Zheng .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (04) :704-717
[9]   Global exponential dissipativity and stabilization of memristor-based recurrent neural networks with time-varying delays [J].
Guo, Zhenyuan ;
Wang, Jun ;
Yan, Zheng .
NEURAL NETWORKS, 2013, 48 :158-172
[10]   Delay-dependent state estimation for delayed neural networks [J].
He, Yong ;
Wang, Qing-Guo ;
Wu, Min ;
Lin, Chong .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (04) :1077-1081