Damage detection of structures using unsupervised fuzzy neural network

C. M. Wen; Shih-Lin Hung; Chiung-Shiann Huang; J. C. Jan

Damage detection of structures using unsupervised fuzzy neural network

C. M. Wen, Shih-Lin Hung, Chiung-Shiann Huang, J. C. Jan

Department of Civil Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This work presents an artificial neural network (ANN) approach for detecting structural damage. An unsupervised neural network which incorporates the fuzzy concept (named the Unsupervised Fuzzy Neural Network, UFN) is adopted to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location termed the Damage Localization Feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single and multiple damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach.

Original language	English
Title of host publication	Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005
Pages	114-119
Number of pages	6
State	Published - Sep 2005
Event	9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005 - Benidorm, Spain Duration: 12 Sep 2005 → 14 Sep 2005

Publication series

Name	Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005

Conference

Conference	9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005
Country/Territory	Spain
City	Benidorm
Period	12/09/05 → 14/09/05

Keywords

Damage detection
Neural network
Structural engineering
Unsupervised fuzzy learning model

Cite this

Wen, C. M., Hung, S-L., Huang, C-S., & Jan, J. C. (2005). Damage detection of structures using unsupervised fuzzy neural network. In Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005 (pp. 114-119). (Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005).

Wen, C. M. ; Hung, Shih-Lin ; Huang, Chiung-Shiann et al. / Damage detection of structures using unsupervised fuzzy neural network. Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005. 2005. pp. 114-119 (Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005).

@inproceedings{ccdf888e711f41038eccf612711ae656,

title = "Damage detection of structures using unsupervised fuzzy neural network",

abstract = "This work presents an artificial neural network (ANN) approach for detecting structural damage. An unsupervised neural network which incorporates the fuzzy concept (named the Unsupervised Fuzzy Neural Network, UFN) is adopted to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location termed the Damage Localization Feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single and multiple damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach.",

keywords = "Damage detection, Neural network, Structural engineering, Unsupervised fuzzy learning model",

author = "Wen, {C. M.} and Shih-Lin Hung and Chiung-Shiann Huang and Jan, {J. C.}",

year = "2005",

month = sep,

language = "English",

isbn = "0889865361",

series = "Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005",

pages = "114--119",

booktitle = "Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005",

note = "null ; Conference date: 12-09-2005 Through 14-09-2005",

}

Wen, CM, Hung, S-L , Huang, C-S & Jan, JC 2005, Damage detection of structures using unsupervised fuzzy neural network. in Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005. Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005, pp. 114-119, 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005, Benidorm, Spain, 12/09/05.

Damage detection of structures using unsupervised fuzzy neural network. / Wen, C. M.; Hung, Shih-Lin ; Huang, Chiung-Shiann et al.

Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005. 2005. p. 114-119 (Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Damage detection of structures using unsupervised fuzzy neural network

AU - Wen, C. M.

AU - Hung, Shih-Lin

AU - Huang, Chiung-Shiann

AU - Jan, J. C.

PY - 2005/9

Y1 - 2005/9

N2 - This work presents an artificial neural network (ANN) approach for detecting structural damage. An unsupervised neural network which incorporates the fuzzy concept (named the Unsupervised Fuzzy Neural Network, UFN) is adopted to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location termed the Damage Localization Feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single and multiple damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach.

AB - This work presents an artificial neural network (ANN) approach for detecting structural damage. An unsupervised neural network which incorporates the fuzzy concept (named the Unsupervised Fuzzy Neural Network, UFN) is adopted to detect localized damage. The structural damage is assumed to take the form of reduced elemental stiffness. The damage site is demonstrated to correlate with the changes in the modal parameters of the structure. Therefore, a feature representing the damage location termed the Damage Localization Feature (DLF) is presented. When the structure experiences damage or change in the structural member, the measured DLF is obtained by analyzing the recorded dynamic responses of the structure. The location of the structural damage then can be identified using the UFN according to the measured DLF information. This study verifies the proposed model using an example involving a five-storey frame building. Both single and multiple damaged sites are considered. The effects of measured noise and the use of incomplete modal data are introduced to inspect the capability of the proposed detection approach.

KW - Damage detection

KW - Neural network

KW - Structural engineering

KW - Unsupervised fuzzy learning model

UR - http://www.scopus.com/inward/record.url?scp=84887216275&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84887216275

SN - 0889865361

SN - 9780889865365

T3 - Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005

SP - 114

EP - 119

BT - Proceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005

Y2 - 12 September 2005 through 14 September 2005

ER -

Damage detection of structures using unsupervised fuzzy neural network

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this