Decentralized stabilization of neural network linearly interconnected systems via T-S fuzzy control

Feng Hsiag Hsiao; Yew Wen Liang; Sheng Dong Xu; Gwo Chuan Lee

doi:10.1115/1.2234492

Decentralized stabilization of neural network linearly interconnected systems via T-S fuzzy control

Feng Hsiag Hsiao^*, Yew Wen Liang, Sheng Dong Xu, Gwo Chuan Lee

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

6 Scopus citations

Abstract

The stabilization problem is considered in this study for a neural-network (NN) linearly interconnected system that consists of a number of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Then, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of closed-loop NN linearly interconnected systems. Subsequently, according to this criterion and the decentralized control scheme, a set of Takagi-Sugeno (T-S) fuzzy controllers is synthesized to stabilize the NN linearly interconnected system. Finally, a numerical example with simulations is given to demonstrate the concepts discussed throughout this paper.

Original language	English
Pages (from-to)	343-351
Number of pages	9
Journal	Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME
Volume	129
Issue number	3
DOIs	https://doi.org/10.1115/1.2234492
State	Published - 05 2007
Externally published	Yes

Access to Document

10.1115/1.2234492

Cite this

@article{3b62e76e1e674d3888b4d98aeb1e5bd8,

title = "Decentralized stabilization of neural network linearly interconnected systems via T-S fuzzy control",

abstract = "The stabilization problem is considered in this study for a neural-network (NN) linearly interconnected system that consists of a number of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Then, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of closed-loop NN linearly interconnected systems. Subsequently, according to this criterion and the decentralized control scheme, a set of Takagi-Sugeno (T-S) fuzzy controllers is synthesized to stabilize the NN linearly interconnected system. Finally, a numerical example with simulations is given to demonstrate the concepts discussed throughout this paper.",

author = "Hsiao, {Feng Hsiag} and Liang, {Yew Wen} and Xu, {Sheng Dong} and Lee, {Gwo Chuan}",

year = "2007",

month = may,

doi = "10.1115/1.2234492",

language = "英语",

volume = "129",

pages = "343--351",

journal = "Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME",

issn = "0022-0434",

publisher = "American Society of Mechanical Engineers (ASME)",

number = "3",

}

TY - JOUR

T1 - Decentralized stabilization of neural network linearly interconnected systems via T-S fuzzy control

AU - Hsiao, Feng Hsiag

AU - Liang, Yew Wen

AU - Xu, Sheng Dong

AU - Lee, Gwo Chuan

PY - 2007/5

Y1 - 2007/5

N2 - The stabilization problem is considered in this study for a neural-network (NN) linearly interconnected system that consists of a number of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Then, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of closed-loop NN linearly interconnected systems. Subsequently, according to this criterion and the decentralized control scheme, a set of Takagi-Sugeno (T-S) fuzzy controllers is synthesized to stabilize the NN linearly interconnected system. Finally, a numerical example with simulations is given to demonstrate the concepts discussed throughout this paper.

AB - The stabilization problem is considered in this study for a neural-network (NN) linearly interconnected system that consists of a number of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Then, based on the LDI state-space representation, a stability criterion in terms of Lyapunov's direct method is derived to guarantee the asymptotic stability of closed-loop NN linearly interconnected systems. Subsequently, according to this criterion and the decentralized control scheme, a set of Takagi-Sugeno (T-S) fuzzy controllers is synthesized to stabilize the NN linearly interconnected system. Finally, a numerical example with simulations is given to demonstrate the concepts discussed throughout this paper.

UR - http://www.scopus.com/inward/record.url?scp=34250851296&partnerID=8YFLogxK

U2 - 10.1115/1.2234492

DO - 10.1115/1.2234492

M3 - 文献综述

AN - SCOPUS:34250851296

SN - 0022-0434

VL - 129

SP - 343

EP - 351

JO - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

JF - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

IS - 3

ER -

Decentralized stabilization of neural network linearly interconnected systems via T-S fuzzy control

Abstract

Access to Document

Other files and links

Fingerprint

Cite this