表紙画像

Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network

The modern application of frequency response function (FRF) with artificial neural networks (ANN) has become one of the leading methods in vibration-based damage detection approach. However, since full-size empirically obtained FRF data is used as ANN input, a broad composition ANN input layer serie...

詳細記述

保存先:
書誌詳細
主要な著者: Padil, K. H., Bakhary, N., Hassan, W. N. F., Darus, N.
フォーマット: 論文
言語:English
出版事項: Penerbit UTHM 2021
主題:
TA Engineering (General). Civil engineering (General)
オンライン･アクセス:http://eprints.utm.my/id/eprint/96562/1/KhairulHPadil2021_UncertaintiesConsiderationinEmpiricalFrequency.pdf
http://eprints.utm.my/id/eprint/96562/
http://dx.doi.org/10.30880/ijie.2021.13.03.025
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
id my.utm.96562
record_format eprints
spelling my.utm.965622022-07-28T06:33:10Z http://eprints.utm.my/id/eprint/96562/ Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network Padil, K. H. Bakhary, N. Hassan, W. N. F. Darus, N. TA Engineering (General). Civil engineering (General) The modern application of frequency response function (FRF) with artificial neural networks (ANN) has become one of the leading methods in vibration-based damage detection approach. However, since full-size empirically obtained FRF data is used as ANN input, a broad composition ANN input layer series would occur. Consequently, principal component analysis (PCA) is adopted to compress the FRF data magnitude. Despite this, PCA alone is unable to select the important FRF data features effectively, due to the exceedingly FRF data size in addition with existing uncertainties. Therefore, this study proposed the merger of a non-probabilistic analysis and ANN approach with PCA by considering the uncertainties effect and the inefficiency of using empirical FRF data. The empirical FRF data is obtained from a steel truss bridge structure. The results show that the PoDE values above 95% are measured at the particular executed damage locations and the DMI values show the damage severity at the actual damage locations. Overall, the results show that the proposed method is capable in considering the uncertainties effect on the empirical FRF data for structural damage identification. Penerbit UTHM 2021 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/96562/1/KhairulHPadil2021_UncertaintiesConsiderationinEmpiricalFrequency.pdf Padil, K. H. and Bakhary, N. and Hassan, W. N. F. and Darus, N. (2021) Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network. International Journal of Integrated Engineering, 13 (3). pp. 207-214. ISSN 2229-838X http://dx.doi.org/10.30880/ijie.2021.13.03.025 DOI: 10.30880/ijie.2021.13.03.025
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Padil, K. H.
Bakhary, N.
Hassan, W. N. F.
Darus, N.
Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
description The modern application of frequency response function (FRF) with artificial neural networks (ANN) has become one of the leading methods in vibration-based damage detection approach. However, since full-size empirically obtained FRF data is used as ANN input, a broad composition ANN input layer series would occur. Consequently, principal component analysis (PCA) is adopted to compress the FRF data magnitude. Despite this, PCA alone is unable to select the important FRF data features effectively, due to the exceedingly FRF data size in addition with existing uncertainties. Therefore, this study proposed the merger of a non-probabilistic analysis and ANN approach with PCA by considering the uncertainties effect and the inefficiency of using empirical FRF data. The empirical FRF data is obtained from a steel truss bridge structure. The results show that the PoDE values above 95% are measured at the particular executed damage locations and the DMI values show the damage severity at the actual damage locations. Overall, the results show that the proposed method is capable in considering the uncertainties effect on the empirical FRF data for structural damage identification.
format Article
author Padil, K. H.
Bakhary, N.
Hassan, W. N. F.
Darus, N.
author_facet Padil, K. H.
Bakhary, N.
Hassan, W. N. F.
Darus, N.
author_sort Padil, K. H.
title Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
title_short Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
title_full Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
title_fullStr Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
title_full_unstemmed Uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
title_sort uncertainties consideration in empirical frequency response function data for damage identification based on artificial neural network
publisher Penerbit UTHM
publishDate 2021
url http://eprints.utm.my/id/eprint/96562/1/KhairulHPadil2021_UncertaintiesConsiderationinEmpiricalFrequency.pdf
http://eprints.utm.my/id/eprint/96562/
http://dx.doi.org/10.30880/ijie.2021.13.03.025
_version_ 1739828097466761216
score 13.251813

類似資料