l2 - l∞ state estimation for discrete-time switched neural networks with time-varying delay

被引：10

作者：

Chen, Yonggang ^{[1
,2
]}

Liu, Lili ^{[3
]}

Qian, Wei ^{[4
]}

Liu, Yurong ^{[5
,6
]}

Alsaadi, Fuad E. ^{[6
]}

机构：

[1] Henan Inst Sci & Technol, Postdoctoral Res Base, Xinxiang 453003, Peoples R China

[2] Henan Univ Sci & Technol, Coll Informat Engn, Luoyang 471023, Peoples R China

[3] Henan Inst Sci & Technol, Sch Mech & Elect Engn, Xinxiang 453003, Peoples R China

[4] Henan Polytech Univ, Coll Elect Engn & Automat, Jiaozuo 454000, Peoples R China

[5] Yangzhou Univ, Dept Math, Yangzhou 225002, Jiangsu, Peoples R China

[6] King Abdulaziz Univ, Fac Engn, Jeddah 21589, Saudi Arabia

来源：

NEUROCOMPUTING | 2018年 / 282卷

基金：

中国博士后科学基金;

关键词：

State estimation; Discrete-time; Switched neural networks; Time-varying delay; l(2) - l(infinity) performance; ROBUST STABILITY ANALYSIS; H-INFINITY; SYSTEMS; PARAMETERS; DESIGN;

D O I：

10.1016/j.neucom.2017.12.006

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 is concerned with the l(2) - l(infinity) state estimation problem for discrete-time switched neural networks with time-varying delay. The main objective is to design a mode-dependent state estimator such that the error dynamics is exponentially stable with a weighted l(2) - l(infinity) performance level. By incorporating the novel l(2) - l(infinity) performance analysis approach, the augmented piecewise Lyapunov-like functionals, the discrete Wirtinger-based inequality and the average-dwell-time switching, less conservative sufficient conditions are proposed by means of linear matrix inequalities. A numerical example is given to illustrate the effectiveness and benefits of the obtained results. (c) 2017 Elsevier B.V. All rights reserved.

引用

页码：25 / 31

页数：7

共 49 条

[1]

Ahn CK, 2011, INT J INNOV COMPUT I, V7, P1831

[2]

ANDERSON B. D., 2012, Optimal Filtering

[3]

[Anonymous], 1996, Neural fuzzy systems

[4] Global asymptotic stability of a larger class of neural networks with constant time delay [J].

Arik, S .

PHYSICS LETTERS A, 2003, 311 (06) :504-511

[5] Robust stability analysis for discrete-time uncertain neural networks with leakage time-varying delay [J].

Banu, L. Jarina ;

Balasubramaniam, P. ;

Ratnavelu, K. .

NEUROCOMPUTING, 2015, 151 :808-816

[6] Further results on passivity analysis of delayed neural networks with leakage delay [J].

Chen, Yonggang ;

Fu, Zhumu ;

Liu, Yurong ;

Alsaadi, Fuad E. .

NEUROCOMPUTING, 2017, 224 :135-141

[7] Improved delay-dependent stability conditions for recurrent neural networks with multiple time-varying delays [J].

Chen, Yonggang ;

Fei, Shumin ;

Li, Yongmin .

NONLINEAR DYNAMICS, 2014, 78 (02) :803-812

[8] Stability Analysis of Time-Delay Neural Networks Subject to Stochastic Perturbations [J].

Chen, Yun ;

Zheng, Wei Xing .

IEEE TRANSACTIONS ON CYBERNETICS, 2013, 43 (06) :2122-2134

[9] Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and l2-l8 Performances [J].

Choi, Hyun Duck ;

Ahn, Choon Ki ;

Karimi, Hamid Reza ;

Lim, Myo Taeg .

IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (10) :3195-3207

[10] L2-L∞ Filtering for Takagi-Sugeno fuzzy neural networks based on Wirtinger-type inequalities [J].

Choi, Hyun Duck ;

Ahn, Choon Ki ;

Shi, Peng ;

Lim, Myo Taeg ;

Song, Moon Kyou .

NEUROCOMPUTING, 2015, 153 :117-125

← 1 2 3 4 5 →