A Novel Dual-Branch Transformer with Gated Cross Attention for Remaining Useful Life Prediction of Bearings

Cui, J; Ji, JC; Zhang, T; Cao, L; Chen, Z; Ni, Q

A Novel Dual-Branch Transformer with Gated Cross Attention for Remaining Useful Life Prediction of Bearings

Cui, J Ji, JC Zhang, T Cao, L Chen, Z Ni, Q

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Sensors Journal, 2024, 24, (24), pp. 41410-41423
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1759204.pdf	Published version	6.06 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	Cui, J
dc.contributor.author	Ji, JC
dc.contributor.author	Zhang, T
dc.contributor.author	Cao, L
dc.contributor.author	Chen, Z
dc.contributor.author	Ni, Q https://orcid.org/0000-0001-7537-3934
dc.date.accessioned	2025-01-03T02:17:32Z
dc.date.available	2025-01-03T02:17:32Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Sensors Journal, 2024, 24, (24), pp. 41410-41423
dc.identifier.issn	1530-437X
dc.identifier.issn	1558-1748
dc.identifier.uri	http://hdl.handle.net/10453/182903
dc.description.abstract	Features from different domains in vibration signals offer valuable insights for remaining useful life (RUL) prediction of bearings. While fusing these features can improve the prediction performance, traditional fusion methods lack effective information exchange across domains, limiting adaptive feature fusion. This limitation can lead to the information redundancy and hinder the accurate identification of bearing degradation states. To address these challenges, this study introduces a dual-branch Transformer with gated cross attention (DTGCA), designed to handle and integrate features from different domains for precise RUL prediction. Specifically, one branch processes 1-D time-series feature from the time and frequency domains, while the other branch uses a residual convolutional gated recurrent unit (res-ConvGRU) to handle 2-D time-frequency image features. The proposed gated cross-attention (GCA) mechanism enables adaptive information exchange between the branches, effectively fusing their information to provide a clearer representation of bearing degradation states. The proposed method is validated on the two real run-to-failure datasets. Comprehensive ablation experiments confirm the method's underlying rationality, while the detailed comparative experiments with other approaches clearly demonstrate its superiority.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Sensors Journal
dc.relation.isbasedon	10.1109/JSEN.2024.3485918
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0205 Optical Physics, 0906 Electrical and Electronic Engineering, 0913 Mechanical Engineering
dc.subject.classification	Analytical Chemistry
dc.subject.classification	40 Engineering
dc.title	A Novel Dual-Branch Transformer with Gated Cross Attention for Remaining Useful Life Prediction of Bearings
dc.type	Journal Article
utslib.citation.volume	24
utslib.for	0205 Optical Physics
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0913 Mechanical Engineering
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 Mechanical and Mechatronic Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Transport Research Centre (TRC)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Audio, Acoustics and Vibration (CAAV)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Transport Research Centre (TRC)/Transport Research Centre (TRC) Associate Members
utslib.copyright.status	closed_access	*
dc.date.updated	2025-01-03T02:17:28Z
pubs.issue	24
pubs.publication-status	Published
pubs.volume	24
utslib.citation.issue	24

Abstract:

Features from different domains in vibration signals offer valuable insights for remaining useful life (RUL) prediction of bearings. While fusing these features can improve the prediction performance, traditional fusion methods lack effective information exchange across domains, limiting adaptive feature fusion. This limitation can lead to the information redundancy and hinder the accurate identification of bearing degradation states. To address these challenges, this study introduces a dual-branch Transformer with gated cross attention (DTGCA), designed to handle and integrate features from different domains for precise RUL prediction. Specifically, one branch processes 1-D time-series feature from the time and frequency domains, while the other branch uses a residual convolutional gated recurrent unit (res-ConvGRU) to handle 2-D time-frequency image features. The proposed gated cross-attention (GCA) mechanism enables adaptive information exchange between the branches, effectively fusing their information to provide a clearer representation of bearing degradation states. The proposed method is validated on the two real run-to-failure datasets. Comprehensive ablation experiments confirm the method's underlying rationality, while the detailed comparative experiments with other approaches clearly demonstrate its superiority.

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

http://hdl.handle.net/10453/182903