Deep learning-based reconstruction of missing long-term girder-end displacement data for suspension bridge health monitoring

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Zhi wei Wang
  • Xiao fan Lu
  • Wen ming Zhang
  • Vasileios C. Fragkoulis
  • Michael Beer
  • Yu feng Zhang

Externe Organisationen

  • Southeast University (SEU)
  • The University of Liverpool
  • Tongji University
  • Jiangsu Transportation Institute Co. Ltd.
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer107070
FachzeitschriftComputers and Structures
Jahrgang284
Frühes Online-Datum16 Mai 2023
PublikationsstatusVeröffentlicht - Aug. 2023

Abstract

The flexibility of a suspension bridge usually results in significant longitudinal displacement at the end of the main girder under the joint action of environmental factors and traffic loads. Fluctuation amplitude and accumulation of girder-end displacement (GED) are primary data for the performance evaluation of suspension bridge elements, including expansion joints, supports, and dampers. However, the performance of the bridge structural health monitoring (SHM) system is frequently deteriorated by the long-term continuous GED data loss or anomaly. In this study, this issue of the suspension bridge SHM system was resolved by proposing a deep learning-based framework for reconstructing the missing GED data. Under this framework, a long short-term memory (LSTM) network-based regression model was first built between the ambient temperature data and the thermal-induced low-frequency components of GED data. Next, a U-net-based spectral bandwidth expansion model was applied for the step-by-step generation of vehicle/wind-induced high-frequency GED data terms based on the available low-frequency ones. Finally, a statistical correction strategy was employed to improve the prediction accuracy for the high-frequency GED data fluctuation amplitudes. The trained model for the reconstruction of the missing GED data uses only the air temperature input values in the data loss period. This method is especially lucrative when GED data in all sensor channels are missing. The reliability and efficiency of the proposed model were demonstrated by a case study. Specifically, the problem of reconstructing the missing GED data in the SHM system of the Jiangyin Yangtze River Bridge in China was considered. Using the relative error of cumulative GED as the performance indicator, a reconstruction precision within 10% was obtained.

ASJC Scopus Sachgebiete

Zitieren

Deep learning-based reconstruction of missing long-term girder-end displacement data for suspension bridge health monitoring. / Wang, Zhi wei; Lu, Xiao fan; Zhang, Wen ming et al.
in: Computers and Structures, Jahrgang 284, 107070, 08.2023.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Wang ZW, Lu XF, Zhang WM, Fragkoulis VC, Beer M, Zhang YF. Deep learning-based reconstruction of missing long-term girder-end displacement data for suspension bridge health monitoring. Computers and Structures. 2023 Aug;284:107070. Epub 2023 Mai 16. doi: 10.1016/j.compstruc.2023.107070
Download
@article{1e83a236d512408b86fccf19d5775421,
title = "Deep learning-based reconstruction of missing long-term girder-end displacement data for suspension bridge health monitoring",
abstract = "The flexibility of a suspension bridge usually results in significant longitudinal displacement at the end of the main girder under the joint action of environmental factors and traffic loads. Fluctuation amplitude and accumulation of girder-end displacement (GED) are primary data for the performance evaluation of suspension bridge elements, including expansion joints, supports, and dampers. However, the performance of the bridge structural health monitoring (SHM) system is frequently deteriorated by the long-term continuous GED data loss or anomaly. In this study, this issue of the suspension bridge SHM system was resolved by proposing a deep learning-based framework for reconstructing the missing GED data. Under this framework, a long short-term memory (LSTM) network-based regression model was first built between the ambient temperature data and the thermal-induced low-frequency components of GED data. Next, a U-net-based spectral bandwidth expansion model was applied for the step-by-step generation of vehicle/wind-induced high-frequency GED data terms based on the available low-frequency ones. Finally, a statistical correction strategy was employed to improve the prediction accuracy for the high-frequency GED data fluctuation amplitudes. The trained model for the reconstruction of the missing GED data uses only the air temperature input values in the data loss period. This method is especially lucrative when GED data in all sensor channels are missing. The reliability and efficiency of the proposed model were demonstrated by a case study. Specifically, the problem of reconstructing the missing GED data in the SHM system of the Jiangyin Yangtze River Bridge in China was considered. Using the relative error of cumulative GED as the performance indicator, a reconstruction precision within 10% was obtained.",
keywords = "Data reconstruction, Deep learning, Girder-end displacement (GED), Spectral bandwidth expansion, Structural health monitoring (SHM), Suspension bridge",
author = "Wang, {Zhi wei} and Lu, {Xiao fan} and Zhang, {Wen ming} and Fragkoulis, {Vasileios C.} and Michael Beer and Zhang, {Yu feng}",
note = "Funding Information: The authors gratefully acknowledge the support by the National Key R&D Program of China (No. 2022YFB3706703), the National Natural Science Foundation of China under Grant 52078134, the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX21_0118), and the Scientific Research Foundation of Graduate School of Southeast University (YBPY2129).",
year = "2023",
month = aug,
doi = "10.1016/j.compstruc.2023.107070",
language = "English",
volume = "284",
journal = "Computers and Structures",
issn = "0045-7949",
publisher = "Elsevier Ltd.",

}

Download

TY - JOUR

T1 - Deep learning-based reconstruction of missing long-term girder-end displacement data for suspension bridge health monitoring

AU - Wang, Zhi wei

AU - Lu, Xiao fan

AU - Zhang, Wen ming

AU - Fragkoulis, Vasileios C.

AU - Beer, Michael

AU - Zhang, Yu feng

N1 - Funding Information: The authors gratefully acknowledge the support by the National Key R&D Program of China (No. 2022YFB3706703), the National Natural Science Foundation of China under Grant 52078134, the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX21_0118), and the Scientific Research Foundation of Graduate School of Southeast University (YBPY2129).

PY - 2023/8

Y1 - 2023/8

N2 - The flexibility of a suspension bridge usually results in significant longitudinal displacement at the end of the main girder under the joint action of environmental factors and traffic loads. Fluctuation amplitude and accumulation of girder-end displacement (GED) are primary data for the performance evaluation of suspension bridge elements, including expansion joints, supports, and dampers. However, the performance of the bridge structural health monitoring (SHM) system is frequently deteriorated by the long-term continuous GED data loss or anomaly. In this study, this issue of the suspension bridge SHM system was resolved by proposing a deep learning-based framework for reconstructing the missing GED data. Under this framework, a long short-term memory (LSTM) network-based regression model was first built between the ambient temperature data and the thermal-induced low-frequency components of GED data. Next, a U-net-based spectral bandwidth expansion model was applied for the step-by-step generation of vehicle/wind-induced high-frequency GED data terms based on the available low-frequency ones. Finally, a statistical correction strategy was employed to improve the prediction accuracy for the high-frequency GED data fluctuation amplitudes. The trained model for the reconstruction of the missing GED data uses only the air temperature input values in the data loss period. This method is especially lucrative when GED data in all sensor channels are missing. The reliability and efficiency of the proposed model were demonstrated by a case study. Specifically, the problem of reconstructing the missing GED data in the SHM system of the Jiangyin Yangtze River Bridge in China was considered. Using the relative error of cumulative GED as the performance indicator, a reconstruction precision within 10% was obtained.

AB - The flexibility of a suspension bridge usually results in significant longitudinal displacement at the end of the main girder under the joint action of environmental factors and traffic loads. Fluctuation amplitude and accumulation of girder-end displacement (GED) are primary data for the performance evaluation of suspension bridge elements, including expansion joints, supports, and dampers. However, the performance of the bridge structural health monitoring (SHM) system is frequently deteriorated by the long-term continuous GED data loss or anomaly. In this study, this issue of the suspension bridge SHM system was resolved by proposing a deep learning-based framework for reconstructing the missing GED data. Under this framework, a long short-term memory (LSTM) network-based regression model was first built between the ambient temperature data and the thermal-induced low-frequency components of GED data. Next, a U-net-based spectral bandwidth expansion model was applied for the step-by-step generation of vehicle/wind-induced high-frequency GED data terms based on the available low-frequency ones. Finally, a statistical correction strategy was employed to improve the prediction accuracy for the high-frequency GED data fluctuation amplitudes. The trained model for the reconstruction of the missing GED data uses only the air temperature input values in the data loss period. This method is especially lucrative when GED data in all sensor channels are missing. The reliability and efficiency of the proposed model were demonstrated by a case study. Specifically, the problem of reconstructing the missing GED data in the SHM system of the Jiangyin Yangtze River Bridge in China was considered. Using the relative error of cumulative GED as the performance indicator, a reconstruction precision within 10% was obtained.

KW - Data reconstruction

KW - Deep learning

KW - Girder-end displacement (GED)

KW - Spectral bandwidth expansion

KW - Structural health monitoring (SHM)

KW - Suspension bridge

UR - http://www.scopus.com/inward/record.url?scp=85159497327&partnerID=8YFLogxK

U2 - 10.1016/j.compstruc.2023.107070

DO - 10.1016/j.compstruc.2023.107070

M3 - Article

AN - SCOPUS:85159497327

VL - 284

JO - Computers and Structures

JF - Computers and Structures

SN - 0045-7949

M1 - 107070

ER -

Von denselben Autoren