Auto-Embedding Transformer for Interpretable Few-Shot Fault Diagnosis of Rolling Bearings

Deep-learning-based intelligent diagnosis is a popular method to ensure the safe operation of rolling bearings. However, practical diagnostic tasks are often subject to a lack of labeled data, resulting in poor performance in scenarios with insufficient training samples. Moreover, conventional intel...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on reliability Jg. 73; H. 2; S. 1270 - 1279
Hauptverfasser: Wang, Gang, Liu, Dongdong, Cui, Lingli
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.06.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:0018-9529, 1558-1721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Deep-learning-based intelligent diagnosis is a popular method to ensure the safe operation of rolling bearings. However, practical diagnostic tasks are often subject to a lack of labeled data, resulting in poor performance in scenarios with insufficient training samples. Moreover, conventional intelligent diagnosis methods suffer from a deficiency in interpretability. In this article, an auto-embedding transformer (AET) method is proposed to implement the interpretable few-shot fault diagnosis of rolling bearings. First, an auto-embedding module is developed to improve the embedding quality of the signal, which is designed based on a novel asymmetric convolutional encoder-decoder architecture. This module can leverage the merits of unsupervised learning in data mining and allow the transformer to learn more diagnostic knowledge from limited data. Second, an attention scoring method is proposed that utilizes positionwise attention to quantify the importance of each signal embedding for diagnosis, thereby interpreting the AET method. Experimental results confirm that, even with limited training samples, the AET method outperforms various comparison methods in terms of recognition accuracy and convergence rate. Furthermore, the attention scores assigned to each embedding facilitate the interpretability of the AET method.
AbstractList Deep-learning-based intelligent diagnosis is a popular method to ensure the safe operation of rolling bearings. However, practical diagnostic tasks are often subject to a lack of labeled data, resulting in poor performance in scenarios with insufficient training samples. Moreover, conventional intelligent diagnosis methods suffer from a deficiency in interpretability. In this article, an auto-embedding transformer (AET) method is proposed to implement the interpretable few-shot fault diagnosis of rolling bearings. First, an auto-embedding module is developed to improve the embedding quality of the signal, which is designed based on a novel asymmetric convolutional encoder-decoder architecture. This module can leverage the merits of unsupervised learning in data mining and allow the transformer to learn more diagnostic knowledge from limited data. Second, an attention scoring method is proposed that utilizes positionwise attention to quantify the importance of each signal embedding for diagnosis, thereby interpreting the AET method. Experimental results confirm that, even with limited training samples, the AET method outperforms various comparison methods in terms of recognition accuracy and convergence rate. Furthermore, the attention scores assigned to each embedding facilitate the interpretability of the AET method.
Author Liu, Dongdong
Cui, Lingli
Wang, Gang
Author_xml – sequence: 1
  givenname: Gang
  orcidid: 0000-0002-3084-8825
  surname: Wang
  fullname: Wang, Gang
  email: wangg@emails.bjut.edu.cn
  organization: Key Laboratory of Advanced Manufacturing Technology, Beijing University of Technology, Beijing, China
– sequence: 2
  givenname: Dongdong
  orcidid: 0000-0003-2638-3014
  surname: Liu
  fullname: Liu, Dongdong
  email: liudd@bjut.edu.cn
  organization: Key Laboratory of Advanced Manufacturing Technology, Beijing University of Technology, Beijing, China
– sequence: 3
  givenname: Lingli
  orcidid: 0000-0003-2883-4018
  surname: Cui
  fullname: Cui, Lingli
  email: acuilingli@163.com
  organization: Key Laboratory of Advanced Manufacturing Technology, Beijing University of Technology, Beijing, China
BookMark eNp9kM1LAzEUxINUsK2evXhY8LxtPjbbzbHWVgsFoa4HT0uyfakp26QmWcT_3i3tQTx4Gh7Mb94wA9SzzgJCtwSPCMFiXK5HFFM2YowWXEwuUJ9wXqRkQkkP9TEmRSo4FVdoEMKuO7NMFH30Pm2jS-d7BZuNsduk9NIG7fwefNJJsrQR_MFDlKqBZAFf6euHi8lCtk1MHo3cWhdMSJxO1q5pjgkPIH2n4RpdatkEuDnrEL0t5uXsOV29PC1n01VaU4FjSjhWXRXMMpErybkGPJFcYi1ErQoKXADmCkCpopaUsY1WGQZCsc6hZrlmQ3R_yj1499lCiNXOtd52LyuG82xCGBe8c_GTq_YuBA-6qk2U0TgbvTRNRXB1XLEq19Vxxeq8YseN_3AHb_bSf_9D3J0IAwC_3Ix0PTj7AV3OfyE
CODEN IERQAD
CitedBy_id crossref_primary_10_1109_JIOT_2024_3487989
crossref_primary_10_1109_JIOT_2025_3547957
crossref_primary_10_1088_1361_6501_ad9e1d
crossref_primary_10_1109_JSEN_2024_3516015
crossref_primary_10_1016_j_ress_2025_111271
crossref_primary_10_1109_TR_2024_3507377
crossref_primary_10_1016_j_aei_2025_103813
crossref_primary_10_3390_app14198582
crossref_primary_10_1016_j_engappai_2024_109261
crossref_primary_10_1109_ACCESS_2024_3430010
crossref_primary_10_1109_TR_2025_3540500
crossref_primary_10_1088_1361_6501_adb2b0
crossref_primary_10_1016_j_aei_2024_102708
crossref_primary_10_1088_1361_6501_ad5de7
crossref_primary_10_3390_act14050255
crossref_primary_10_1007_s11071_024_09389_y
crossref_primary_10_3390_s25072254
crossref_primary_10_3390_app142210095
crossref_primary_10_1177_14759217251350560
crossref_primary_10_1063_5_0255451
crossref_primary_10_1088_1361_6501_ad4d15
crossref_primary_10_1109_TII_2024_3438252
crossref_primary_10_1109_TR_2025_3527739
crossref_primary_10_1016_j_ress_2024_110632
crossref_primary_10_1016_j_ress_2025_110830
crossref_primary_10_1016_j_rser_2025_115809
Cites_doi 10.1016/j.renene.2021.12.054
10.1109/tim.2020.3039648
10.1016/j.neucom.2022.04.111
10.1016/j.ymssp.2023.110427
10.1016/j.asoc.2021.108391
10.1007/s11465-021-0650-6
10.1109/TR.2018.2882682
10.1109/TII.2020.2968370
10.1016/j.eswa.2023.120696
10.1109/tim.2022.3169528
10.1016/j.ymssp.2021.108673
10.1109/tim.2022.3163167
10.1109/TPAMI.2022.3152247
10.1109/acc.2005.1470385
10.1109/ICCV48922.2021.00986
10.1016/j.measurement.2022.111228
10.1088/1361-6501/ace98a
10.1109/TR.2022.3215243
10.1016/j.ymssp.2019.106530
10.1109/JSEN.2022.3188646
10.1109/TMECH.2021.3058061
10.1016/j.jmsy.2021.12.003
10.1109/TR.2021.3117732
10.1088/1361-6501/acf390
10.1109/TIE.2022.3140403
10.1109/TSMC.2020.3048950
10.1109/tim.2022.3181933
10.1109/TII.2022.3192597
10.1016/j.ijmecsci.2022.107708
10.1109/JSEN.2020.3008177
10.1109/JSEN.2022.3146151
10.1016/j.neucom.2022.06.066
10.1109/tim.2022.3225013
10.1109/tnnls.2022.3230458
10.1016/j.ymssp.2019.106587
10.1109/TIE.2020.3028821
10.48550/ARXIV.1706.03762
10.1109/CVPR52688.2022.01553
10.1016/j.ymssp.2018.12.051
10.1016/j.ress.2023.109319
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/TR.2023.3328597
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-1721
EndPage 1279
ExternalDocumentID 10_1109_TR_2023_3328597
10315955
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 52075008; 52305086
  funderid: 10.13039/501100001809
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
5VS
6IK
8WZ
97E
A6W
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
OCL
P2P
RIA
RIE
RNS
TN5
VH1
VJK
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c290t-150b44903496ba55fe07a5a0f99cb82e59e05beebb8ca233dfb40e120f6ec36f3
IEDL.DBID RIE
ISICitedReferencesCount 46
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001111908000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9529
IngestDate Sun Jun 29 15:24:00 EDT 2025
Tue Nov 18 22:31:27 EST 2025
Sat Nov 29 01:54:37 EST 2025
Wed Aug 27 02:00:11 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c290t-150b44903496ba55fe07a5a0f99cb82e59e05beebb8ca233dfb40e120f6ec36f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-2883-4018
0000-0003-2638-3014
0000-0002-3084-8825
PQID 3064713595
PQPubID 85456
PageCount 10
ParticipantIDs proquest_journals_3064713595
ieee_primary_10315955
crossref_citationtrail_10_1109_TR_2023_3328597
crossref_primary_10_1109_TR_2023_3328597
PublicationCentury 2000
PublicationDate 2024-June
2024-6-00
20240601
PublicationDateYYYYMMDD 2024-06-01
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-June
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on reliability
PublicationTitleAbbrev TR
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
ref12
ref34
ref15
ref37
ref14
ref36
Kingma (ref43)
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
van der Maaten (ref44) 2008; 9
ref17
ref39
ref16
ref38
ref19
ref18
ref24
ref23
ref25
ref20
ref41
ref22
ref21
Yu (ref42) 2014
ref28
ref27
ref29
ref8
Dosovitskiy (ref26)
ref7
ref9
ref4
ref3
ref6
ref5
ref40
References_xml – ident: ref21
  doi: 10.1016/j.renene.2021.12.054
– ident: ref4
  doi: 10.1109/tim.2020.3039648
– ident: ref22
  doi: 10.1016/j.neucom.2022.04.111
– ident: ref12
  doi: 10.1016/j.ymssp.2023.110427
– ident: ref36
  doi: 10.1016/j.asoc.2021.108391
– ident: ref39
  doi: 10.1007/s11465-021-0650-6
– ident: ref3
  doi: 10.1109/TR.2018.2882682
– ident: ref20
  doi: 10.1109/TII.2020.2968370
– year: 2014
  ident: ref42
  article-title: Case Western Reserve University Bearing Data Center
– ident: ref15
  doi: 10.1016/j.eswa.2023.120696
– ident: ref29
  doi: 10.1109/tim.2022.3169528
– ident: ref34
  doi: 10.1016/j.ymssp.2021.108673
– ident: ref5
  doi: 10.1109/tim.2022.3163167
– ident: ref27
  doi: 10.1109/TPAMI.2022.3152247
– ident: ref2
  doi: 10.1109/acc.2005.1470385
– ident: ref28
  doi: 10.1109/ICCV48922.2021.00986
– start-page: 1
  ident: ref43
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc. Int. Conf. Learn. Representations
– ident: ref41
  doi: 10.1016/j.measurement.2022.111228
– start-page: 2750
  ident: ref26
  article-title: An image is worth 1616 words: Transformers for image recognition at scale
  publication-title: Proc. Int. Conf. Learn. Representations
– ident: ref7
  doi: 10.1088/1361-6501/ace98a
– ident: ref23
  doi: 10.1109/TR.2022.3215243
– ident: ref31
  doi: 10.1016/j.ymssp.2019.106530
– ident: ref10
  doi: 10.1109/JSEN.2022.3188646
– ident: ref32
  doi: 10.1109/TMECH.2021.3058061
– ident: ref24
  doi: 10.1016/j.jmsy.2021.12.003
– ident: ref11
  doi: 10.1109/TR.2021.3117732
– ident: ref8
  doi: 10.1088/1361-6501/acf390
– ident: ref18
  doi: 10.1109/TIE.2022.3140403
– ident: ref40
  doi: 10.1109/TSMC.2020.3048950
– ident: ref30
  doi: 10.1109/tim.2022.3181933
– ident: ref1
  doi: 10.1109/TII.2022.3192597
– ident: ref9
  doi: 10.1016/j.ijmecsci.2022.107708
– ident: ref17
  doi: 10.1109/JSEN.2020.3008177
– volume: 9
  start-page: 2579
  year: 2008
  ident: ref44
  article-title: Visualizing data using t-SNE
  publication-title: J. Mach. Learn. Res.
– ident: ref13
  doi: 10.1109/JSEN.2022.3146151
– ident: ref14
  doi: 10.1016/j.neucom.2022.06.066
– ident: ref16
  doi: 10.1109/tim.2022.3225013
– ident: ref35
  doi: 10.1109/tnnls.2022.3230458
– ident: ref6
  doi: 10.1016/j.ymssp.2019.106587
– ident: ref19
  doi: 10.1109/TIE.2020.3028821
– ident: ref25
  doi: 10.48550/ARXIV.1706.03762
– ident: ref33
  doi: 10.1109/CVPR52688.2022.01553
– ident: ref37
  doi: 10.1016/j.ymssp.2018.12.051
– ident: ref38
  doi: 10.1016/j.ress.2023.109319
SSID ssj0014498
Score 2.569148
Snippet Deep-learning-based intelligent diagnosis is a popular method to ensure the safe operation of rolling bearings. However, practical diagnostic tasks are often...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1270
SubjectTerms Autoencoder
Convolution
Data mining
Deep learning
Diagnostic systems
Embedding
Fault diagnosis
Feature extraction
few-shot diagnosis
interpretability
Modules
Roller bearings
Rolling bearings
Signal quality
transformer
Transformers
Unsupervised learning
Vibrations
Title Auto-Embedding Transformer for Interpretable Few-Shot Fault Diagnosis of Rolling Bearings
URI https://ieeexplore.ieee.org/document/10315955
https://www.proquest.com/docview/3064713595
Volume 73
WOSCitedRecordID wos001111908000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-1721
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014498
  issn: 0018-9529
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwMhECbWeNCDzxqr1XDw4IV2d4ECR1-NJ2O0JnraADtEk9o17Vb_vgtLfcR48MQeYENmGGaAme9D6LgQA-GkTYn3xYQ5x4hJBRAKmmaFNDSzRSCbENfX8uFB3cRi9VALAwAh-Qx6_jO85Relnfursn6gJFCct1BLCNEUa30-GTCm4rZbWzDPVMTxSRPVH932PEt4j1IP1yZ-uKDAqfJrIw7eZbjxz3ltovUYRuLTRu9baAkm22jtG7jgDno8nVcluXwxUHj_hEeLEBWmuG7wV7qhGQMewju5eyorPNTzcYUvmgy85xkuHY7A3fistgp_sd5G98PL0fkViUQKxGYqqUgd9JlaPAEc3mjOHSRCc504payRGXAFCTcAxkirM0oLZ1gCaZa4AVg6cHQXLU_KCewhrCVIZpmpIzXLhCzkQKdUqBScsplTuoN6C9nmNqKMe7KLcR5OG4nKR7e5V0YeldFBJ58DXhuAjb-7tr3sv3VrxN5B3YX28miBs9yfrDz9oOL7fww7QKv131mT99VFy9V0Dodoxb5Vz7PpUVhcH4DbzMg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PTxQxFH5BJFEPCIphBaQHD166zPTHTntEYQMRNwbHBE-TtvMaSdYdsjur_77TThcxhAOnzqHNNO_19b22730fwPu6GBVeuZwGX0yF94LavEDK0XBWK8uZqyPZRDGZqKsr_TUVq8daGESMyWc4DJ_xLb9u3DJclR1FSgIt5RN4KoVgeV-udftoIIROG29nw5LphOSTZ_qovBwGnvAh5wGwrfjPCUVWlXtbcfQv45ePnNkWbKZAkhz3mt-GNZy9ghd34AVfw4_jZdvQ018W6-ChSLkKUnFOuob8Szi0UyRj_EO__WxaMjbLaUtO-hy86wVpPEnQ3eRjZxfhan0Hvo9Py09nNFEpUMd01tIu7LOdeCI8vDVSeswKI03mtXZWMZQaM2kRrVXOMM5rb0WGOcv8CB0fef4G1mfNDHeBGIVKOGG7WM2JQtVqZHJe6By9dsxrM4DhSraVSzjjge5iWsXzRqar8rIKyqiSMgbw4XbATQ-x8XDXnSD7O916sQ9gf6W9Ktngogpnq0BAqOXbB4YdwrOz8stFdXE--bwHz7s_iT4LbB_W2_kSD2DD_W6vF_N3caH9BVGP0A8
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Auto-Embedding+Transformer+for+Interpretable+Few-Shot+Fault+Diagnosis+of+Rolling+Bearings&rft.jtitle=IEEE+transactions+on+reliability&rft.au=Wang%2C+Gang&rft.au=Liu%2C+Dongdong&rft.au=Cui%2C+Lingli&rft.date=2024-06-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9529&rft.eissn=1558-1721&rft.volume=73&rft.issue=2&rft.spage=1270&rft_id=info:doi/10.1109%2FTR.2023.3328597&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9529&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9529&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9529&client=summon