Delay-dependent H∞ control for discrete-time uncertain recurrent neural networks with intrerval time-varying delay

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This paper deals with the problem of delay-dependent robust H control for discrete-time recurrent neural networks (DRNNs) with norm-bounded parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. For the robust stabilization problem, a state feedback controller is designed to ensure global robust stability of the closed-loop system about its equilibrium point for all admissible uncertainties, while for the robust H control problem, attention is focused on the design of a state feedback controller such that in addition to the requirement of the global robust stability, a prescribed H performance level for all delays to satisfy both the lower bound and upper bound of the interval time-varying delay is also required to be achieved. A linear matrix inequality approach is developed to solve these problems. It is shown that the desired state feedback controller can be constructed by solving certain LMIs. A numerical example is provided to demonstrate the effectiveness and applicability of the proposed results. ICIC International

Original languageEnglish
Pages (from-to)3483-3493
Number of pages11
JournalInternational Journal of Innovative Computing, Information and Control
Volume5
Issue number10
Publication statusPublished - 2009 Oct 1

Fingerprint

Recurrent neural networks
Delay-dependent
Recurrent Neural Networks
Time-varying Delay
State feedback
State Feedback
Interval Time-varying Delay
Discrete-time
Robust Stability
Global Stability
Controller
Controllers
Norm-bounded Uncertainties
Robust Stabilization
Activation Function
Parameter Uncertainty
Linear matrix inequalities
Equilibrium Point
Closed loop systems
Closed-loop System

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Information Systems
  • Software
  • Theoretical Computer Science

Cite this

@article{8f7554056e624f9694d81621fca8e9d4,
title = "Delay-dependent H∞ control for discrete-time uncertain recurrent neural networks with intrerval time-varying delay",
abstract = "This paper deals with the problem of delay-dependent robust H ∞ control for discrete-time recurrent neural networks (DRNNs) with norm-bounded parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. For the robust stabilization problem, a state feedback controller is designed to ensure global robust stability of the closed-loop system about its equilibrium point for all admissible uncertainties, while for the robust H∞ control problem, attention is focused on the design of a state feedback controller such that in addition to the requirement of the global robust stability, a prescribed H∞ performance level for all delays to satisfy both the lower bound and upper bound of the interval time-varying delay is also required to be achieved. A linear matrix inequality approach is developed to solve these problems. It is shown that the desired state feedback controller can be constructed by solving certain LMIs. A numerical example is provided to demonstrate the effectiveness and applicability of the proposed results. ICIC International",
author = "Lu, {Chien Yu} and Shyr, {Wen Jye} and Yao, {Kai Chao} and Liao, {Chin Wen} and Huang, {Chuan Kuei}",
year = "2009",
month = "10",
day = "1",
language = "English",
volume = "5",
pages = "3483--3493",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "10",

}

TY - JOUR

T1 - Delay-dependent H∞ control for discrete-time uncertain recurrent neural networks with intrerval time-varying delay

AU - Lu, Chien Yu

AU - Shyr, Wen Jye

AU - Yao, Kai Chao

AU - Liao, Chin Wen

AU - Huang, Chuan Kuei

PY - 2009/10/1

Y1 - 2009/10/1

N2 - This paper deals with the problem of delay-dependent robust H ∞ control for discrete-time recurrent neural networks (DRNNs) with norm-bounded parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. For the robust stabilization problem, a state feedback controller is designed to ensure global robust stability of the closed-loop system about its equilibrium point for all admissible uncertainties, while for the robust H∞ control problem, attention is focused on the design of a state feedback controller such that in addition to the requirement of the global robust stability, a prescribed H∞ performance level for all delays to satisfy both the lower bound and upper bound of the interval time-varying delay is also required to be achieved. A linear matrix inequality approach is developed to solve these problems. It is shown that the desired state feedback controller can be constructed by solving certain LMIs. A numerical example is provided to demonstrate the effectiveness and applicability of the proposed results. ICIC International

AB - This paper deals with the problem of delay-dependent robust H ∞ control for discrete-time recurrent neural networks (DRNNs) with norm-bounded parameter uncertainties and interval time-varying delay. The activation functions are assumed to be globally Lipschitz continuous. For the robust stabilization problem, a state feedback controller is designed to ensure global robust stability of the closed-loop system about its equilibrium point for all admissible uncertainties, while for the robust H∞ control problem, attention is focused on the design of a state feedback controller such that in addition to the requirement of the global robust stability, a prescribed H∞ performance level for all delays to satisfy both the lower bound and upper bound of the interval time-varying delay is also required to be achieved. A linear matrix inequality approach is developed to solve these problems. It is shown that the desired state feedback controller can be constructed by solving certain LMIs. A numerical example is provided to demonstrate the effectiveness and applicability of the proposed results. ICIC International

UR - http://www.scopus.com/inward/record.url?scp=70350492295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350492295&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:70350492295

VL - 5

SP - 3483

EP - 3493

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 10

ER -