Robust passive filtering for neutral-type neural networks with time-varying discrete and unbounded distributed delays

被引：57

作者：

Lin, Xue ^{[1
]}

Zhang, Xian ^{[1
]}

Wang, Yantao ^{[1
]}

机构：

[1] Heilongjiang Univ, Sch Math Sci, Harbin 150080, Peoples R China

来源：

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS | 2013年 / 350卷 / 05期

关键词：

MARKOVIAN JUMPING PARAMETERS; STABILITY ANALYSIS; EXPONENTIAL STABILITY; STATE ESTIMATION; INTERVAL; SYSTEMS; CRITERIA;

D O I：

10.1016/j.jfranklin.2013.01.021

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The passive filtering problem is studied for a class of neutral-type neural networks with time-varying discrete and unbounded distributed delays. Based on the passive theory, a sufficient condition for the existence of the robust passive filter is given. By introducing an appropriate Lyapunov-Krasovskii functional and using Jensen's inequality technique to deal with its derivative, the criterion which ensures error dynamic system to be strictly passive with dissipation gamma > 0 is presented in the form of nonlinear matrix inequality. In order to solve the nonlinear problem, a cone complementarity linearization (CCL) algorithm is proposed. Furthermore, when the norm-bounded parameter uncertainties appear in the class of neural networks, the corresponding robust passive filtering problem is also investigated. Three examples are given to demonstrate the effectiveness of the proposed method. (C) 2013 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.

引用

页码：966 / 989

页数：24

共 37 条

[1] Linear matrix inequality approach to passive filtering for delayed neural networks [J].

Ahn, C. K. .

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING, 2010, 224 (I8) :1040-1047

[2] Analog integrated circuits for the Lotka-Volterra competitive neural networks [J].

Asai, T ;

Ohtani, M ;

Yonezu, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :1222-1231

[3] Passivity analysis for neural networks of neutral type with Markovian jumping parameters and time delay in the leakage term [J].

Balasubramaniam, P. ;

Nagamani, G. ;

Rakkiyappan, R. .

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2011, 16 (11) :4422-4437

[4] Global Passivity Analysis of Interval Neural Networks with Discrete and Distributed Delays of Neutral Type [J].

Balasubramaniam, P. ;

Nagamani, G. ;

Rakkiyappan, R. .

NEURAL PROCESSING LETTERS, 2010, 32 (02) :109-130

[5] Methods for linear systems of circuit delay differential equations of neutral type [J].

Bellen, A ;

Guglielmi, N ;

Ruehli, AE .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1999, 46 (01) :212-216

[6]

Boyd S., 1994, P 39 IEEE C DEC CONT, V15

[7] Less conservative results of state estimation for neural networks with time-varying delay [J].

Chen, Yonggang ;

Bi, Weiping ;

Li, Wenlin ;

Wu, Yuanyuan .

NEUROCOMPUTING, 2010, 73 (7-9) :1324-1331

[8] CELLULAR NEURAL NETWORKS - APPLICATIONS [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290

[9] Robust stability analysis of uncertain stochastic neural networks with interval time-varying delay [J].

Feng, Wei ;

Yang, Simon X. ;

Fu, Wei ;

Wu, Haixia .

CHAOS SOLITONS & FRACTALS, 2009, 41 (01) :414-424

[10]

Gouaisbaut F., 2006, P IFAC WORKSH TIM DE, P1

← 1 2 3 4 →