Dealing with fault dynamics in nonlinear systems via double neural network units

Yong D. SONG; Xiao H. LIAO; Cortney BELDEN; Zhi YANG

doi:10.1007/11427469_14

Dealing with fault dynamics in nonlinear systems via double neural network units

Yong D. SONG^*
, Xiao H. LIAO
, Cortney BELDEN
, Zhi YANG

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

Abstract

Most fault detection and accommodation methods have traditionally been derived based on linear system modeling techniques, which restrict the type of practical failure situation that can be modeled. In this paper we explore a methodology for fault accommodation in nonlinear dynamic systems. A new control scheme is derived by incorporating two neural network (NN) units to effectively attenuate and compensate uncertain dynamics due to unpredictable faults. It is shown that the method is independent of the nature of the fault. Numerical simulations are included to demonstrate the effectiveness of the proposed method. © Springer-Verlag Berlin Heidelberg 2005.

Original language	English
Title of host publication	Advances in Neural Networks: ISNN 2005: Second International Symposium on Neural Networks. Proceedings
Editors	Jun WANG, Xiao-Feng LIAO, Zhang YI
Publisher	Springer Berlin Heidelberg
Pages	92-97
Number of pages	6
ISBN (Electronic)	9783540320692
ISBN (Print)	9783540259145
DOIs	https://doi.org/10.1007/11427469_14
Publication status	Published - 2005
Externally published	Yes

Access to Document

10.1007/11427469_14

Cite this

@inproceedings{77b72c05804243bd93a399fe5aacbae8,

title = "Dealing with fault dynamics in nonlinear systems via double neural network units",

abstract = "Most fault detection and accommodation methods have traditionally been derived based on linear system modeling techniques, which restrict the type of practical failure situation that can be modeled. In this paper we explore a methodology for fault accommodation in nonlinear dynamic systems. A new control scheme is derived by incorporating two neural network (NN) units to effectively attenuate and compensate uncertain dynamics due to unpredictable faults. It is shown that the method is independent of the nature of the fault. Numerical simulations are included to demonstrate the effectiveness of the proposed method. {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.",

author = "SONG, \{Yong D.\} and LIAO, \{Xiao H.\} and Cortney BELDEN and Zhi YANG",

year = "2005",

doi = "10.1007/11427469\_14",

language = "English",

isbn = "9783540259145",

pages = "92--97",

editor = "Jun WANG and Xiao-Feng LIAO and Zhang YI",

booktitle = "Advances in Neural Networks: ISNN 2005: Second International Symposium on Neural Networks. Proceedings",

publisher = "Springer Berlin Heidelberg",

}

Dealing with fault dynamics in nonlinear systems via double neural network units. / SONG, Yong D.; LIAO, Xiao H.; BELDEN, Cortney et al.
Advances in Neural Networks: ISNN 2005: Second International Symposium on Neural Networks. Proceedings. ed. / Jun WANG; Xiao-Feng LIAO; Zhang YI. Springer Berlin Heidelberg, 2005. p. 92-97.

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Dealing with fault dynamics in nonlinear systems via double neural network units

AU - SONG, Yong D.

AU - LIAO, Xiao H.

AU - BELDEN, Cortney

AU - YANG, Zhi

PY - 2005

Y1 - 2005

N2 - Most fault detection and accommodation methods have traditionally been derived based on linear system modeling techniques, which restrict the type of practical failure situation that can be modeled. In this paper we explore a methodology for fault accommodation in nonlinear dynamic systems. A new control scheme is derived by incorporating two neural network (NN) units to effectively attenuate and compensate uncertain dynamics due to unpredictable faults. It is shown that the method is independent of the nature of the fault. Numerical simulations are included to demonstrate the effectiveness of the proposed method. © Springer-Verlag Berlin Heidelberg 2005.

AB - Most fault detection and accommodation methods have traditionally been derived based on linear system modeling techniques, which restrict the type of practical failure situation that can be modeled. In this paper we explore a methodology for fault accommodation in nonlinear dynamic systems. A new control scheme is derived by incorporating two neural network (NN) units to effectively attenuate and compensate uncertain dynamics due to unpredictable faults. It is shown that the method is independent of the nature of the fault. Numerical simulations are included to demonstrate the effectiveness of the proposed method. © Springer-Verlag Berlin Heidelberg 2005.

UR - https://www.scopus.com/pages/publications/24944460624

U2 - 10.1007/11427469_14

DO - 10.1007/11427469_14

M3 - Conference paper (refereed)

AN - SCOPUS:24944460624

SN - 9783540259145

SP - 92

EP - 97

BT - Advances in Neural Networks: ISNN 2005: Second International Symposium on Neural Networks. Proceedings

A2 - WANG, Jun

A2 - LIAO, Xiao-Feng

A2 - YI, Zhang

PB - Springer Berlin Heidelberg

ER -

Dealing with fault dynamics in nonlinear systems via double neural network units

Abstract

Access to Document

Other files and links

Fingerprint

Cite this