Neural network H∞ chaos synchronization

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

This paper proposes a new neural network H∞ synchronization (NNHS) scheme for unknown chaotic systems. In the proposed framework, a dynamic neural network is constructed as an alternative to approximate the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the NNHS controller and the learning law are presented to reduce the effect of disturbance to an H∞ norm constraint. It is shown that finding the NNHS controller and the learning law can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed NNHS scheme.

Original languageEnglish
Pages (from-to)295-302
Number of pages8
JournalNonlinear Dynamics
Volume60
Issue number3
DOIs
Publication statusPublished - 2010 May 1

Fingerprint

Chaos Synchronization
Chaos theory
Synchronization
Neural Networks
Neural networks
Chaotic systems
Chaotic System
Matrix Inequality
Linear Inequalities
Linear matrix inequalities
Dynamic Neural Networks
Controller
Controllers
Convex Optimization
Convex optimization
Optimization Methods
Disturbance
Norm
Unknown
Numerical Examples

Keywords

  • Dynamic neural networks
  • H∞ synchronization
  • Linear matrix inequality (LMI)
  • Unknown chaotic systems
  • Weight learning law

ASJC Scopus subject areas

  • Applied Mathematics
  • Mechanical Engineering
  • Aerospace Engineering
  • Ocean Engineering
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Neural network H∞ chaos synchronization. / Ahn, Choon Ki.

In: Nonlinear Dynamics, Vol. 60, No. 3, 01.05.2010, p. 295-302.

Research output: Contribution to journalArticle

@article{60d62bb123f840ed9efc2a0f1e314fa6,
title = "Neural network H∞ chaos synchronization",
abstract = "This paper proposes a new neural network H∞ synchronization (NNHS) scheme for unknown chaotic systems. In the proposed framework, a dynamic neural network is constructed as an alternative to approximate the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the NNHS controller and the learning law are presented to reduce the effect of disturbance to an H∞ norm constraint. It is shown that finding the NNHS controller and the learning law can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed NNHS scheme.",
keywords = "Dynamic neural networks, H∞ synchronization, Linear matrix inequality (LMI), Unknown chaotic systems, Weight learning law",
author = "Ahn, {Choon Ki}",
year = "2010",
month = "5",
day = "1",
doi = "10.1007/s11071-009-9596-7",
language = "English",
volume = "60",
pages = "295--302",
journal = "Nonlinear Dynamics",
issn = "0924-090X",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Neural network H∞ chaos synchronization

AU - Ahn, Choon Ki

PY - 2010/5/1

Y1 - 2010/5/1

N2 - This paper proposes a new neural network H∞ synchronization (NNHS) scheme for unknown chaotic systems. In the proposed framework, a dynamic neural network is constructed as an alternative to approximate the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the NNHS controller and the learning law are presented to reduce the effect of disturbance to an H∞ norm constraint. It is shown that finding the NNHS controller and the learning law can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed NNHS scheme.

AB - This paper proposes a new neural network H∞ synchronization (NNHS) scheme for unknown chaotic systems. In the proposed framework, a dynamic neural network is constructed as an alternative to approximate the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the NNHS controller and the learning law are presented to reduce the effect of disturbance to an H∞ norm constraint. It is shown that finding the NNHS controller and the learning law can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed NNHS scheme.

KW - Dynamic neural networks

KW - H∞ synchronization

KW - Linear matrix inequality (LMI)

KW - Unknown chaotic systems

KW - Weight learning law

UR - http://www.scopus.com/inward/record.url?scp=77953359438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953359438&partnerID=8YFLogxK

U2 - 10.1007/s11071-009-9596-7

DO - 10.1007/s11071-009-9596-7

M3 - Article

AN - SCOPUS:77953359438

VL - 60

SP - 295

EP - 302

JO - Nonlinear Dynamics

JF - Nonlinear Dynamics

SN - 0924-090X

IS - 3

ER -