Exponential H∞ stable learning method for Takagi-Sugeno fuzzy delayed neural networks: A convex optimization approach

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

In this paper, we propose some new results on stability for Takagi-Sugeno fuzzy delayed neural networks with a stable learning method. Based on the Lyapunov-Krasovskii approach, for the first time, a new learning method is presented to not only guarantee the exponential stability of Takagi-Sugeno fuzzy neural networks with time-delay, but also reduce the effect of external disturbance to a prescribed attenuation level. The proposed learning method can be obtained by solving a convex optimization problem which is represented in terms of a set of linear matrix inequalities (LMIs). An illustrative example is given to demonstrate the effectiveness of the proposed learning method.

Original languageEnglish
Pages (from-to)887-895
Number of pages9
JournalComputers and Mathematics with Applications
Volume63
Issue number5
DOIs
Publication statusPublished - 2012 Mar 1
Externally publishedYes

Fingerprint

Delayed Neural Networks
Fuzzy neural networks
Convex optimization
Convex Optimization
Asymptotic stability
Linear matrix inequalities
Time delay
Fuzzy Neural Network
Exponential Stability
Attenuation
Lyapunov
Matrix Inequality
Linear Inequalities
Time Delay
Disturbance
Optimization Problem
Learning
Demonstrate

Keywords

  • Exponential H∞ stability
  • Linear matrix inequality (LMI)
  • Lyapunov-Krasovskii approach
  • Networks
  • Takagi-Sugeno fuzzy delayed neural
  • Weight learning method

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Modelling and Simulation
  • Computational Mathematics

Cite this

@article{524d6ee4790b4b16b464093ec16dfbe2,
title = "Exponential H∞ stable learning method for Takagi-Sugeno fuzzy delayed neural networks: A convex optimization approach",
abstract = "In this paper, we propose some new results on stability for Takagi-Sugeno fuzzy delayed neural networks with a stable learning method. Based on the Lyapunov-Krasovskii approach, for the first time, a new learning method is presented to not only guarantee the exponential stability of Takagi-Sugeno fuzzy neural networks with time-delay, but also reduce the effect of external disturbance to a prescribed attenuation level. The proposed learning method can be obtained by solving a convex optimization problem which is represented in terms of a set of linear matrix inequalities (LMIs). An illustrative example is given to demonstrate the effectiveness of the proposed learning method.",
keywords = "Exponential H∞ stability, Linear matrix inequality (LMI), Lyapunov-Krasovskii approach, Networks, Takagi-Sugeno fuzzy delayed neural, Weight learning method",
author = "Ahn, {Choon Ki}",
year = "2012",
month = "3",
day = "1",
doi = "10.1016/j.camwa.2011.11.054",
language = "English",
volume = "63",
pages = "887--895",
journal = "Computers and Mathematics with Applications",
issn = "0898-1221",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Exponential H∞ stable learning method for Takagi-Sugeno fuzzy delayed neural networks

T2 - A convex optimization approach

AU - Ahn, Choon Ki

PY - 2012/3/1

Y1 - 2012/3/1

N2 - In this paper, we propose some new results on stability for Takagi-Sugeno fuzzy delayed neural networks with a stable learning method. Based on the Lyapunov-Krasovskii approach, for the first time, a new learning method is presented to not only guarantee the exponential stability of Takagi-Sugeno fuzzy neural networks with time-delay, but also reduce the effect of external disturbance to a prescribed attenuation level. The proposed learning method can be obtained by solving a convex optimization problem which is represented in terms of a set of linear matrix inequalities (LMIs). An illustrative example is given to demonstrate the effectiveness of the proposed learning method.

AB - In this paper, we propose some new results on stability for Takagi-Sugeno fuzzy delayed neural networks with a stable learning method. Based on the Lyapunov-Krasovskii approach, for the first time, a new learning method is presented to not only guarantee the exponential stability of Takagi-Sugeno fuzzy neural networks with time-delay, but also reduce the effect of external disturbance to a prescribed attenuation level. The proposed learning method can be obtained by solving a convex optimization problem which is represented in terms of a set of linear matrix inequalities (LMIs). An illustrative example is given to demonstrate the effectiveness of the proposed learning method.

KW - Exponential H∞ stability

KW - Linear matrix inequality (LMI)

KW - Lyapunov-Krasovskii approach

KW - Networks

KW - Takagi-Sugeno fuzzy delayed neural

KW - Weight learning method

UR - http://www.scopus.com/inward/record.url?scp=84865616192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865616192&partnerID=8YFLogxK

U2 - 10.1016/j.camwa.2011.11.054

DO - 10.1016/j.camwa.2011.11.054

M3 - Article

AN - SCOPUS:84865616192

VL - 63

SP - 887

EP - 895

JO - Computers and Mathematics with Applications

JF - Computers and Mathematics with Applications

SN - 0898-1221

IS - 5

ER -