Transfer learning based bridge damage detection: Leveraging time-frequency features

Talaei, S; Zhu, X; Li, J; Yu, Y; Chan, THT

Transfer learning based bridge damage detection: Leveraging time-frequency features

Talaei, S

Zhu, X

Li, J Yu, Y

Chan, THT

Permalink

Publisher:: ELSEVIER SCIENCE INC
Publication Type:: Journal Article
Citation:: Structures, 2023, 57
Issue Date:: 2023-11-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0263822323004269-main.pdf	Published version	3.26 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Talaei, S https://orcid.org/0000-0001-6400-4367
dc.contributor.author	Zhu, X https://orcid.org/0000-0001-5083-9320
dc.contributor.author	Li, J
dc.contributor.author	Yu, Y https://orcid.org/0000-0001-9592-8191
dc.contributor.author	Chan, THT
dc.date.accessioned	2024-01-12T04:34:34Z
dc.date.available	2024-01-12T04:34:34Z
dc.date.issued	2023-11-01
dc.identifier.citation	Structures, 2023, 57
dc.identifier.issn	2352-0124
dc.identifier.issn	2352-0124
dc.identifier.uri	http://hdl.handle.net/10453/174374
dc.description.abstract	Bridges are a crucial part of the transport infrastructure network, and their safety and operational conditions need to be ensured. An early warning of damage is valuable for condition-based maintenance to avoid costly consequence including structural collapse. Dynamic behaviour of bridge structures can be used as indicators for their health status. Machine Learning techniques allow high-dimensional connections between the structures’ vibrational responses and their state of health. In this research, a novel transfer learning-based approach is presented for identifying the location of damage in concrete bridges utilising the time–frequency characteristics from dynamic responses of the bridge under moving vehicles. Convolutional neural networks (CNNs) are used to extract discriminative features from the time-varying input data of vehicle-bridge interaction. Pre-trained CNNs are then fine-tuned for multiple damage classification tasks. The performance of the proposed method is evaluated by comparing it with a variety of pre-trained networks and optimized classification algorithms. Effects of the noise level, vehicle speed, and sensor location on the predicted results are also studied. The numerical results show that the proposed method can precisely locate the damage on concrete bridges using only a single sensor on the bridge deck. The method has valuable potential for practical application for localising the bridge structural damage with further fine-tuning using the field measurement data.
dc.language	English
dc.publisher	ELSEVIER SCIENCE INC
dc.relation	http://purl.org/au-research/grants/arc/DP220102045
dc.relation	http://purl.org/au-research/grants/arc/DP230100806
dc.relation.ispartof	Structures
dc.relation.isbasedon	10.1016/j.istruc.2023.105052
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0905 Civil Engineering, 1202 Building
dc.subject.classification	4005 Civil engineering
dc.title	Transfer learning based bridge damage detection: Leveraging time-frequency features
dc.type	Journal Article
utslib.citation.volume	57
utslib.for	0905 Civil Engineering
utslib.for	1202 Building
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-01-12T04:34:32Z
pubs.publication-status	Published
pubs.volume	57

Abstract:

Bridges are a crucial part of the transport infrastructure network, and their safety and operational conditions need to be ensured. An early warning of damage is valuable for condition-based maintenance to avoid costly consequence including structural collapse. Dynamic behaviour of bridge structures can be used as indicators for their health status. Machine Learning techniques allow high-dimensional connections between the structures’ vibrational responses and their state of health. In this research, a novel transfer learning-based approach is presented for identifying the location of damage in concrete bridges utilising the time–frequency characteristics from dynamic responses of the bridge under moving vehicles. Convolutional neural networks (CNNs) are used to extract discriminative features from the time-varying input data of vehicle-bridge interaction. Pre-trained CNNs are then fine-tuned for multiple damage classification tasks. The performance of the proposed method is evaluated by comparing it with a variety of pre-trained networks and optimized classification algorithms. Effects of the noise level, vehicle speed, and sensor location on the predicted results are also studied. The numerical results show that the proposed method can precisely locate the damage on concrete bridges using only a single sensor on the bridge deck. The method has valuable potential for practical application for localising the bridge structural damage with further fine-tuning using the field measurement data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/174374