An LMI approach to passivity analysis for uncertain neural networks with multiple time-varying delays

Chien Yu Lu, Chin Wen Liao, Hsun Heng Tsai, Jason Sheng-Hon Tsai, Jui Chuan Cheng

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper deals with the problem of Passivity analysis for neural networks with multiple time-varying delays subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. New passivity conditions are proposed by using Lyapunov-Krasovskii functionals and the free-weighting matrix method to relax the existing requirement of derivative of time delays of the system. Passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using recently developed standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness.

Original languageEnglish
Pages (from-to)307-314
Number of pages8
JournalInternational Journal of Electrical Engineering
Volume14
Issue number4
Publication statusPublished - 2007 Aug 1

Fingerprint

Linear matrix inequalities
Time delay
Chemical activation
Derivatives
Neural networks
Uncertainty

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{ec0b6877fbdc48e690466991de5c10b5,
title = "An LMI approach to passivity analysis for uncertain neural networks with multiple time-varying delays",
abstract = "This paper deals with the problem of Passivity analysis for neural networks with multiple time-varying delays subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. New passivity conditions are proposed by using Lyapunov-Krasovskii functionals and the free-weighting matrix method to relax the existing requirement of derivative of time delays of the system. Passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using recently developed standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness.",
author = "Lu, {Chien Yu} and Liao, {Chin Wen} and Tsai, {Hsun Heng} and Tsai, {Jason Sheng-Hon} and Cheng, {Jui Chuan}",
year = "2007",
month = "8",
day = "1",
language = "English",
volume = "14",
pages = "307--314",
journal = "International Journal of Electrical Engineering",
issn = "1812-3031",
publisher = "Chinese Institute of Electrical Engineering",
number = "4",

}

An LMI approach to passivity analysis for uncertain neural networks with multiple time-varying delays. / Lu, Chien Yu; Liao, Chin Wen; Tsai, Hsun Heng; Tsai, Jason Sheng-Hon; Cheng, Jui Chuan.

In: International Journal of Electrical Engineering, Vol. 14, No. 4, 01.08.2007, p. 307-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An LMI approach to passivity analysis for uncertain neural networks with multiple time-varying delays

AU - Lu, Chien Yu

AU - Liao, Chin Wen

AU - Tsai, Hsun Heng

AU - Tsai, Jason Sheng-Hon

AU - Cheng, Jui Chuan

PY - 2007/8/1

Y1 - 2007/8/1

N2 - This paper deals with the problem of Passivity analysis for neural networks with multiple time-varying delays subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. New passivity conditions are proposed by using Lyapunov-Krasovskii functionals and the free-weighting matrix method to relax the existing requirement of derivative of time delays of the system. Passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using recently developed standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness.

AB - This paper deals with the problem of Passivity analysis for neural networks with multiple time-varying delays subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. New passivity conditions are proposed by using Lyapunov-Krasovskii functionals and the free-weighting matrix method to relax the existing requirement of derivative of time delays of the system. Passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by using recently developed standard algorithms. Two illustrative examples are provided to demonstrate the effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=37149020478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37149020478&partnerID=8YFLogxK

M3 - Article

VL - 14

SP - 307

EP - 314

JO - International Journal of Electrical Engineering

JF - International Journal of Electrical Engineering

SN - 1812-3031

IS - 4

ER -