Delay-dependent exponential stability of neural networks with variable delay : an LMI approach

Wu-Hua Chen; Xiaomei Lu; Zhi-Hong Guan; Wei Xing Zheng

doi:10.1109/TCSII.2006.881824

Delay-dependent exponential stability of neural networks with variable delay : an LMI approach

Wu-Hua Chen, Xiaomei Lu, Zhi-Hong Guan, Wei Xing Zheng

School of Computer, Data & Mathematical Sciences

Research output: Contribution to journal › Article

86 Citations (Scopus)

Abstract

This brief focuses on the problem of delay-dependent stability analysis of neural networks with variable delay. Two types of variable delay are considered: one is differentiable and has bounded derivative; the other one is continuous and may vary very fast. By introducing a new type of Lyapunov-Krasovskii functional, new delay-dependent sufficient conditions for exponential stability of delayed neural networks are derived in terms of linear matrix inequalities. We also obtain delay-independent stability criteria. Two examples are presented which show our results are less conservative than the existing stability criteria.

Original language	English
Pages (from-to)	837-842
Number of pages	6
Journal	IEEE Transactions on Circuits and Systems II: Express Briefs
Volume	53
Issue number	9
DOIs	https://doi.org/10.1109/TCSII.2006.881824
Publication status	Published - Sept 2006

Keywords

delay-dependent criteria
exponential stability
matrix inequalities
neural networks (computer science)
variable delay
neural networks
linear matrix inequality (LMI)
Delay-dependent criteria

Access to Document

10.1109/TCSII.2006.881824

Cite this

@article{82d6f880b8584db4b0cfbf0b3e2cb25f,

title = "Delay-dependent exponential stability of neural networks with variable delay : an LMI approach",

abstract = "This brief focuses on the problem of delay-dependent stability analysis of neural networks with variable delay. Two types of variable delay are considered: one is differentiable and has bounded derivative; the other one is continuous and may vary very fast. By introducing a new type of Lyapunov-Krasovskii functional, new delay-dependent sufficient conditions for exponential stability of delayed neural networks are derived in terms of linear matrix inequalities. We also obtain delay-independent stability criteria. Two examples are presented which show our results are less conservative than the existing stability criteria.",

keywords = "delay-dependent criteria, exponential stability, matrix inequalities, neural networks (computer science), variable delay, neural networks, linear matrix inequality (LMI), Delay-dependent criteria",

author = "Wu-Hua Chen and Xiaomei Lu and Zhi-Hong Guan and Zheng, {Wei Xing}",

year = "2006",

month = sep,

doi = "10.1109/TCSII.2006.881824",

language = "English",

volume = "53",

pages = "837--842",

journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",

issn = "1549-7747",

publisher = "Institute of Electrical and Electronics Engineers",

number = "9",

}

TY - JOUR

T1 - Delay-dependent exponential stability of neural networks with variable delay : an LMI approach

AU - Chen, Wu-Hua

AU - Lu, Xiaomei

AU - Guan, Zhi-Hong

AU - Zheng, Wei Xing

PY - 2006/9

Y1 - 2006/9

N2 - This brief focuses on the problem of delay-dependent stability analysis of neural networks with variable delay. Two types of variable delay are considered: one is differentiable and has bounded derivative; the other one is continuous and may vary very fast. By introducing a new type of Lyapunov-Krasovskii functional, new delay-dependent sufficient conditions for exponential stability of delayed neural networks are derived in terms of linear matrix inequalities. We also obtain delay-independent stability criteria. Two examples are presented which show our results are less conservative than the existing stability criteria.

AB - This brief focuses on the problem of delay-dependent stability analysis of neural networks with variable delay. Two types of variable delay are considered: one is differentiable and has bounded derivative; the other one is continuous and may vary very fast. By introducing a new type of Lyapunov-Krasovskii functional, new delay-dependent sufficient conditions for exponential stability of delayed neural networks are derived in terms of linear matrix inequalities. We also obtain delay-independent stability criteria. Two examples are presented which show our results are less conservative than the existing stability criteria.

KW - delay-dependent criteria

KW - exponential stability

KW - matrix inequalities

KW - neural networks (computer science)

KW - variable delay

KW - neural networks

KW - linear matrix inequality (LMI)

KW - Delay-dependent criteria

UR - http://hdl.handle.net/1959.7/uws:4254

UR - https://doi.org/10.1109/TCSII.2006.881824

UR - http://www.scopus.com/inward/record.url?scp=34047141013&partnerID=8YFLogxK

U2 - 10.1109/TCSII.2006.881824

DO - 10.1109/TCSII.2006.881824

M3 - Article

SN - 1549-7747

VL - 53

SP - 837

EP - 842

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

IS - 9

ER -

Delay-dependent exponential stability of neural networks with variable delay : an LMI approach

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this