Multifault Feature Wasserstein Generative Adversarial Networks for Fault Diagnosis in Unbalanced Data

Due to the limitation of industrial conditions in production, raw sensor data are always shown as an unbalanced dataset, characterized by abundant normal operational data and scarce fault instances. This unbalance can degrade the performance of conventional fault diagnosis methods, leading to reduce...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on instrumentation and measurement Jg. 74; S. 1 - 9
Hauptverfasser:	Ren, Weibo, Wang, Zhijian, Chen, Zhongxin, Zhao, Shun, Dong, Lei, Li, Yanfeng, Fan, Xin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Accuracy Artificial intelligence Bearing-unbalanced data Data mining Datasets Fault diagnosis Generative adversarial networks multiencoder denoising autoencoder (DAE) Training Wasserstein generative adversarial networks (WGANs)
ISSN:	0018-9456, 1557-9662
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Due to the limitation of industrial conditions in production, raw sensor data are always shown as an unbalanced dataset, characterized by abundant normal operational data and scarce fault instances. This unbalance can degrade the performance of conventional fault diagnosis methods, leading to reduced accuracy and unstable model training. To address this challenge in bearing fault diagnosis, this article proposes a multifault feature Wasserstein generative adversarial network (MFF-WGAN) to enhance diagnostic precision. First, the framework employs a multiencoder denoising autoencoder (DAE) architecture to mitigate noise interference in raw sensor data. Subsequently, the proposed MFF-WGAN integrates label information into its adversarial loss function to enable simultaneous generation of diverse fault categories, while incorporating interclass feature discrepancies to refine sample quality. Finally, the developed multifault feature Wasserstein generation adversarial network is tested on the Case Western Reserve University bearing dataset and the laboratory bearing dataset. Computational results show that the proposed method can generate high-quality bearing samples with multiple faults effectively, which can obtain a higher diagnosis accuracy of 99.01% and 97.71% compared with the existing methods.
AbstractList	Due to the limitation of industrial conditions in production, raw sensor data are always shown as an unbalanced dataset, characterized by abundant normal operational data and scarce fault instances. This unbalance can degrade the performance of conventional fault diagnosis methods, leading to reduced accuracy and unstable model training. To address this challenge in bearing fault diagnosis, this article proposes a multifault feature Wasserstein generative adversarial network (MFF-WGAN) to enhance diagnostic precision. First, the framework employs a multiencoder denoising autoencoder (DAE) architecture to mitigate noise interference in raw sensor data. Subsequently, the proposed MFF-WGAN integrates label information into its adversarial loss function to enable simultaneous generation of diverse fault categories, while incorporating interclass feature discrepancies to refine sample quality. Finally, the developed multifault feature Wasserstein generation adversarial network is tested on the Case Western Reserve University bearing dataset and the laboratory bearing dataset. Computational results show that the proposed method can generate high-quality bearing samples with multiple faults effectively, which can obtain a higher diagnosis accuracy of 99.01% and 97.71% compared with the existing methods.
Author	Wang, Zhijian Dong, Lei Li, Yanfeng Ren, Weibo Fan, Xin Zhao, Shun Chen, Zhongxin
Author_xml	– sequence: 1 givenname: Weibo orcidid: 0000-0001-8666-4585 surname: Ren fullname: Ren, Weibo email: rwb012@126.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 2 givenname: Zhijian orcidid: 0000-0002-6794-2065 surname: Wang fullname: Wang, Zhijian email: wangzhijian1013@163.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 3 givenname: Zhongxin orcidid: 0000-0001-5757-2972 surname: Chen fullname: Chen, Zhongxin email: czx19910305@163.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 4 givenname: Shun orcidid: 0009-0007-9526-2458 surname: Zhao fullname: Zhao, Shun email: 2271763827@qq.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 5 givenname: Lei orcidid: 0000-0001-6151-8848 surname: Dong fullname: Dong, Lei email: 13754892010@163.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 6 givenname: Yanfeng orcidid: 0000-0002-5884-5060 surname: Li fullname: Li, Yanfeng email: yanfengli0002@163.com organization: School of Mechanical Engineering, North University of China, Taiyuan, China – sequence: 7 givenname: Xin orcidid: 0000-0001-6450-234X surname: Fan fullname: Fan, Xin email: xfan2021@nuc.edu.cn organization: School of Material Science and Engineering, North University of China, Taiyuan, China
BookMark	eNp9kDtLBTEQRoMoeH30FhYB673msckmpahXBR-NYrnMZicSXbOa5Cr-e1evIFjYzMDwnfngbJH1OEYkZI-zOefMHt5eXM0FE2oulWHGsDUy40o1ldVarJMZY9xUtlZ6k2zl_MgYa3TdzAheLYcSPEyTLhDKMiG9h5wx5YIh0jOMmKCEN6RH_dt0hRRgoNdY3sf0lKkfE1180ycBHuKYQ6YTdhc7GCA67OkJFNghGx6GjLs_e5vcLU5vj8-ry5uzi-Ojy8oJW5eqk15ozTjUWqLRhoNUvWg6KaxyzlpnhXRdp6xRErlvetN7QKmFt05pD3KbHKz-vqTxdYm5tI_jMsWpspVC1LqxWqkpxVYpl8acE_r2JYVnSB8tZ-2XzHaS2X7JbH9kToj-g7hQJi1jLAnC8B-4vwIDIv72cFYzZoT8BGK0hHw
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_3390_machines13080633
Cites_doi	10.1109/access.2019.2924003 10.1016/j.inffus.2023.102005 10.1109/tim.2023.3345910 10.1016/j.measurement.2022.110826 10.1016/j.asoc.2023.110176 10.1109/tim.2025.3544700 10.1109/tim.2024.3413128 10.1016/j.measurement.2021.110460 10.1016/j.knosys.2020.105764 10.1016/j.aei.2024.102514 10.1109/mis.2022.3168356 10.3390/lubricants11020074 10.1109/tnnls.2024.3383467 10.1007/s10489-019-01624-z 10.1016/j.isatra.2021.11.040 10.1016/j.ymssp.2021.108018 10.1007/s10845-019-01522-8 10.1177/1475921719893594 10.1109/tnnls.2024.3483954 10.1109/icccnt56998.2023.10306417 10.1016/j.ymssp.2015.04.021 10.1109/tie.2021.3108726 10.1007/s40430-023-04142-9 10.1016/j.engappai.2021.104279 10.1016/j.chemolab.2022.104711 10.1016/j.ress.2024.110001 10.1109/tie.2017.2774777 10.1016/j.knosys.2020.105845 10.1145/1143844.1143945 10.1016/j.ymssp.2019.106587 10.1016/j.ins.2017.09.013
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TIM.2025.3580880
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Xplore Digital Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	9
ExternalDocumentID	10_1109_TIM_2025_3580880 11040082
Genre	orig-research
GrantInformation_xml	– fundername: Special Guiding Project for the Transformation of Scientific and Technological Achievements grantid: 202304021301012 – fundername: Shanxi Scholarship Council of China grantid: 2021-128 funderid: 10.13039/501100003398 – fundername: Special Fund for Science and Technology Innovation Teams of Shanxi Province grantid: 202304051001013 – fundername: Science and Technology Major Special Program of Shanxi grantid: 202301150401011 – fundername: Shanxi Basic Research Program grantid: 20210302124356 – fundername: Opening Project of Shanxi Key Laboratory of Advanced Manufacturing Technology grantid: XJZZ202102 – fundername: National Natural Science Foundation of China grantid: 52405566; 52275139; 52305140 funderid: 10.13039/501100001809 – fundername: Fundamental Research Program of Shanxi Province grantid: 202403021222145; 202403021222177 funderid: 10.13039/501100004480
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ VH1 VJK AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c294t-b3f26601a463e8681a35d27b3295cc99c923cbb59853e1f7d8dfae362f9c56fa3
IEDL.DBID	RIE
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001518786900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9456
IngestDate	Thu Aug 14 02:12:13 EDT 2025 Sat Nov 29 07:42:48 EST 2025 Tue Nov 18 22:21:56 EST 2025 Wed Aug 27 02:13:56 EDT 2025
IsPeerReviewed	true
IsScholarly	true
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-c294t-b3f26601a463e8681a35d27b3295cc99c923cbb59853e1f7d8dfae362f9c56fa3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6794-2065 0000-0002-5884-5060 0000-0001-8666-4585 0000-0001-5757-2972 0000-0001-6450-234X 0000-0001-6151-8848 0009-0007-9526-2458
PQID	3224679655
PQPubID	85462
PageCount	9
ParticipantIDs	ieee_primary_11040082 proquest_journals_3224679655 crossref_primary_10_1109_TIM_2025_3580880 crossref_citationtrail_10_1109_TIM_2025_3580880
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
PublicationYear	2025
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 ref12 ref15 ref14 ref31 ref30 ref11 ref10 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref18 doi: 10.1109/access.2019.2924003 – ident: ref1 doi: 10.1016/j.inffus.2023.102005 – ident: ref4 doi: 10.1109/tim.2023.3345910 – ident: ref19 doi: 10.1016/j.measurement.2022.110826 – ident: ref27 doi: 10.1016/j.asoc.2023.110176 – ident: ref21 doi: 10.1109/tim.2025.3544700 – ident: ref22 doi: 10.1109/tim.2024.3413128 – ident: ref23 doi: 10.1016/j.measurement.2021.110460 – ident: ref24 doi: 10.1016/j.knosys.2020.105764 – ident: ref5 doi: 10.1016/j.aei.2024.102514 – ident: ref17 doi: 10.1109/mis.2022.3168356 – ident: ref20 doi: 10.3390/lubricants11020074 – ident: ref3 doi: 10.1109/tnnls.2024.3383467 – ident: ref10 doi: 10.1007/s10489-019-01624-z – ident: ref15 doi: 10.1016/j.isatra.2021.11.040 – ident: ref14 doi: 10.1016/j.ymssp.2021.108018 – ident: ref11 doi: 10.1007/s10845-019-01522-8 – ident: ref25 doi: 10.1177/1475921719893594 – ident: ref6 doi: 10.1109/tnnls.2024.3483954 – ident: ref16 doi: 10.1109/icccnt56998.2023.10306417 – ident: ref31 doi: 10.1016/j.ymssp.2015.04.021 – ident: ref7 doi: 10.1109/tie.2021.3108726 – ident: ref12 doi: 10.1007/s40430-023-04142-9 – ident: ref29 doi: 10.1016/j.engappai.2021.104279 – ident: ref26 doi: 10.1016/j.chemolab.2022.104711 – ident: ref28 doi: 10.1016/j.ress.2024.110001 – ident: ref30 doi: 10.1109/tie.2017.2774777 – ident: ref13 doi: 10.1016/j.knosys.2020.105845 – ident: ref8 doi: 10.1145/1143844.1143945 – ident: ref2 doi: 10.1016/j.ymssp.2019.106587 – ident: ref9 doi: 10.1016/j.ins.2017.09.013
SSID	ssj0007647
Score	2.4429657
Snippet	Due to the limitation of industrial conditions in production, raw sensor data are always shown as an unbalanced dataset, characterized by abundant normal...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Accuracy Artificial intelligence Bearing-unbalanced data Data mining Datasets Fault diagnosis Generative adversarial networks multiencoder denoising autoencoder (DAE) Training Wasserstein generative adversarial networks (WGANs)
Title	Multifault Feature Wasserstein Generative Adversarial Networks for Fault Diagnosis in Unbalanced Data
URI	https://ieeexplore.ieee.org/document/11040082 https://www.proquest.com/docview/3224679655
Volume	74
WOSCitedRecordID	wos001518786900002&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 Digital Library customDbUrl: eissn: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB20KOjBb7FaJQcvHrbtfmSzOYpa9GDxUNHbkmRnoSCtdFt_vzPZbRVEwcuyh0xY9iWZl2TmDcBlEcvQuoSFbo0KiN-GgUYVBgWmLlLEb11pfbEJNRxmr6_6qUlW97kwiOiDz7DLr_4uv5i6BR-V9chVJeyz1mGduqmTtVbLrkqTWiAzpBlMtGB5J9nXvdHDI-0EI9nlO7-MFSC_-SBfVOXHSuzdy2D3nx-2BzsNjxTXNfD7sIaTA9j-pi54AJs-utNVh4A-zbY09BTM-RYzFC_GJ1pysUtRa0_zwid8gebK8LAUwzpEvBJEbMXAW9_WkXnjSpDZ88RyYKTDQtyauTmC58Hd6OY-aOorBC7SyTywcUnuuR-aJI0xS7PQxLKIlI0jLZ3T2hH5c9ZKTS4dw1IVWVEaJI9XaifT0sTH0JpMJ3gCAo1yyiokizgpmIZaokoay0RSN2nSht7yj-euER_nGhhvud-E9HVOGOWMUd5g1IarlcV7LbzxR9sjxuSrXQNHGzpLVPNmalZ5zBJ6SqdSnv5idgZb3Ht90NKB1ny2wHPYcB_zcTW78KPuExHL1Cw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1BT9swFH4abBPswAYU0Y0NH3bhENokdhwf0aBqNag4FI1bZDsvUiXUoqbl9_OekwISYhKXKAe_JMqz_X223_sewO8yVbHzkoVurY6I38aRQR1HJWY-0cRvfeVCsQk9Hue3t-a6TVYPuTCIGILP8JRvw1l-Ofcr3irrEVRJxqwN-KikTPpNutbTxKsz2UhkxjSGiRisTyX7pjcZXdFaMFGnfOqXswbkCxQKZVVezcUBYAZf3_lp32CnZZLirHH9LnzA2R58eaEvuAefQ3ynr_cBQ6JtZekqmPWtFij-2ZBqyeUuRaM-zVOfCCWaa8sdU4ybIPFaELUVg2B93sTmTWtBZjczx6GRHktxbpe2AzeDi8mfYdRWWIh8YuQycmlFAN2PrcxSzLM8tqkqE-3SxCjvjfFE_7xzyhCoY1zpMi8ri4R5lfEqq2x6AJuz-QwPQaDVXjuNZJHKkomoI7JksJKKHpPJLvTWf7zwrfw4V8G4K8IypG8K8lHBPipaH3Xh5MnivpHe-E_bDvvkuV3rji4crb1atIOzLlIW0dMmU-r7G2bHsDWcXF0Wl6Px3x-wzW9qtl2OYHO5WOFP-OQfltN68Sv0wEdDrtdz
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=Multifault+Feature+Wasserstein+Generative+Adversarial+Networks+for+Fault+Diagnosis+in+Unbalanced+Data&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Ren%2C+Weibo&rft.au=Wang%2C+Zhijian&rft.au=Chen%2C+Zhongxin&rft.au=Zhao%2C+Shun&rft.date=2025&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=74&rft.spage=1&rft.epage=9&rft_id=info:doi/10.1109%2FTIM.2025.3580880&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIM_2025_3580880
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon