Lightweight CNN Architecture Design Based on Spatial-Temporal Tensor and Its Application in Bearing Fault Diagnosis

Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task. Despite the great success of convolutional neural network (CNN) in feature extraction, most of them are based on manual tuning, and it is not easy...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on instrumentation and measurement Jg. 73; S. 1 - 12
Hauptverfasser:	Wang, Zan, Lu, Hui, Shi, Yuhui, Wang, Xianpeng
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Artificial neural networks Automatic architecture design bearing fault diagnosis (BFD) convolutional neural network (CNN) Convolutional neural networks Deep learning Fault diagnosis Feature extraction Floating point arithmetic genetic algorithm Genetic algorithms Lightweight Machine learning Mathematical analysis Rotating machinery Space exploration Tensors Vibrations
ISSN:	0018-9456, 1557-9662
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task. Despite the great success of convolutional neural network (CNN) in feature extraction, most of them are based on manual tuning, and it is not easy to determine a unified CNN architecture with an effective balance between accuracy and computational resources [parameters and floating point operations (FLOPs)]. In this article, an automatic CNN architecture design method called AUTO-CNN is proposed to address the above issues. First, a novel representation learning method (RLM) based on spatial-temporal tensors (STTs) is proposed, in which AUTO-CNN can use 2-D multiscale convolutions to capture more feature hierarchy, i.e., temporal variabilities and spatial characteristics. Second, unlike most of the current nontask-specific studies that establish deeper and more complex networks for better performance, this article investigates lightweight CNNs with limited resources under task-specific applications. Finally, to speed up the design process, an efficient hierarchical encoding strategy and space exploration strategy are proposed to avoid inefficient architecture generation and reduce CNNs training time. Experiments on four real-world BFD tasks demonstrate that the proposed method outperforms the peer competitors, including machine learning, deep learning, and other CNN-based methods.
AbstractList	Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task. Despite the great success of convolutional neural network (CNN) in feature extraction, most of them are based on manual tuning, and it is not easy to determine a unified CNN architecture with an effective balance between accuracy and computational resources [parameters and floating point operations (FLOPs)]. In this article, an automatic CNN architecture design method called AUTO-CNN is proposed to address the above issues. First, a novel representation learning method (RLM) based on spatial-temporal tensors (STTs) is proposed, in which AUTO-CNN can use 2-D multiscale convolutions to capture more feature hierarchy, i.e., temporal variabilities and spatial characteristics. Second, unlike most of the current nontask-specific studies that establish deeper and more complex networks for better performance, this article investigates lightweight CNNs with limited resources under task-specific applications. Finally, to speed up the design process, an efficient hierarchical encoding strategy and space exploration strategy are proposed to avoid inefficient architecture generation and reduce CNNs training time. Experiments on four real-world BFD tasks demonstrate that the proposed method outperforms the peer competitors, including machine learning, deep learning, and other CNN-based methods.
Author	Wang, Zan Shi, Yuhui Wang, Xianpeng Lu, Hui
Author_xml	– sequence: 1 givenname: Zan orcidid: 0000-0002-9809-5655 surname: Wang fullname: Wang, Zan email: by2002141@buaa.edu.cn organization: School of Electronic and Information Engineering, Beihang University, Beijing, China – sequence: 2 givenname: Hui orcidid: 0000-0001-9455-4597 surname: Lu fullname: Lu, Hui email: mluhui@buaa.edu.cn organization: School of Electronic and Information Engineering, Beihang University, Beijing, China – sequence: 3 givenname: Yuhui orcidid: 0000-0002-8840-723X surname: Shi fullname: Shi, Yuhui email: shiyh@sustech.edu.cn organization: Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, School of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China – sequence: 4 givenname: Xianpeng orcidid: 0000-0001-8132-9446 surname: Wang fullname: Wang, Xianpeng email: wangxianpeng@ise.neu.edu.cn organization: National Frontiers Science Center for Industrial Intelligence and Systems Optimization and the Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education, Shenyang, China
BookMark	eNp9kDtPwzAURi0EEuWxMzBYYk7xK3Y8lvKqVMpAmSPXuWldpU6wXSH-PSntgBhY7l2-cz_dc4aOfesBoStKhpQSfTufvAwZYXzIOZeC50doQPNcZVpKdowGhNAi0yKXp-gsxjUhREmhBihO3XKVPmE38Xg2w6NgVy6BTdsA-B6iW3p8ZyJUuPX4rTPJmSabw6Zrg2nwHHxsAza-wpMU8ajrGmf7TJ91PQcmOL_Ej2bbJHzvzNK30cULdFKbJsLlYZ-j98eH-fg5m74-TcajaWYZUSkzBoSylWBgdb2oOSNVoU2h85wVTAOpZCUJUK5ZJWtjba0XpgKltBCcF8D4ObrZ3-1C-7GFmMp1uw2-ryyZJkIqwTjtU2SfsqGNMUBddsFtTPgqKSl3astebblTWx7U9oj8g1iXfr5OwbjmP_B6DzoA-NXDOVE059_XIojs
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_1007_s11227_025_07493_3 crossref_primary_10_1109_JSEN_2025_3591231 crossref_primary_10_1109_TIM_2025_3575982 crossref_primary_10_1088_1361_6501_adcadc crossref_primary_10_1088_1361_6501_adcce6 crossref_primary_10_1109_TIM_2025_3544322 crossref_primary_10_1109_TITS_2024_3474704 crossref_primary_10_1109_TIM_2025_3551952 crossref_primary_10_1109_TIM_2024_3440384 crossref_primary_10_1109_TIM_2025_3551427
Cites_doi	10.1016/j.ress.2023.109319 10.1016/j.psep.2021.03.016 10.1016/j.jsv.2014.02.038 10.1109/ACCESS.2021.3065195 10.1016/j.ymssp.2023.110427 10.1109/TIM.2022.3168929 10.1109/TNNLS.2021.3059784 10.1088/1361-6501/ac3b0b 10.3390/s22176570 10.1007/s00170-021-08126-8 10.1109/CVPR.2017.243 10.1021/ie300072q 10.1214/aoms/1177704472 10.1016/j.isatra.2020.08.010 10.1109/TIM.2021.3071232 10.1109/TIM.2022.3212542 10.1109/tevc.2023.3290172 10.1016/j.neucom.2022.04.111 10.1109/TIM.2019.2933119 10.3390/app112210889 10.4236/jcc.2014.29004 10.1155/2019/4031795 10.1109/TIE.2017.2752151 10.1109/TIM.2021.3072131 10.1109/ACCESS.2021.3097353 10.1016/j.jmsy.2023.07.012 10.1109/TIM.2021.3080402 10.1109/ICDM.2008.17 10.1016/j.jmsy.2021.03.022 10.1109/TIE.2017.2774777 10.1155/2021/1221462 10.1007/s11265-019-01463-8 10.1109/CVPR.2016.90 10.1109/TII.2012.2214394 10.1021/acs.iecr.9b03399 10.1109/TIM.2022.3188058
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 7U5 8FD L7M
DOI	10.1109/TIM.2023.3336435
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 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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	12
ExternalDocumentID	10_1109_TIM_2023_3336435 10330715
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62371030; 61827901; 62073067 funderid: 10.13039/501100001809 – fundername: Beijing Municipal Natural Science Foundation grantid: 4222008 funderid: 10.13039/501100004826
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-c207t-aae47cd42ec9fbf320d89a89552829e0d6d60e1392d6faccf9bade77944338e23
IEDL.DBID	RIE
ISSN	0018-9456
IngestDate	Mon Jun 30 08:08:24 EDT 2025 Sat Nov 29 08:06:41 EST 2025 Tue Nov 18 22:17:42 EST 2025 Wed Aug 27 01:42:30 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-c207t-aae47cd42ec9fbf320d89a89552829e0d6d60e1392d6faccf9bade77944338e23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8840-723X 0000-0001-9455-4597 0000-0001-8132-9446 0000-0002-9809-5655
PQID	2904674231
PQPubID	85462
PageCount	12
ParticipantIDs	proquest_journals_2904674231 ieee_primary_10330715 crossref_primary_10_1109_TIM_2023_3336435 crossref_citationtrail_10_1109_TIM_2023_3336435
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
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 ref31 ref30 ref11 ref10 ref1 ref39 ref38 ref19 ref18 Howard (ref16) 2017 ref24 ref23 ref26 Lessmeier (ref2) ref25 ref20 ref41 ref22 ref21 ref28 ref27 ref29 ref8 ref7 Tan (ref17) ref9 ref4 ref3 ref6 ref5 Schölkopf (ref33); 12 ref40 (ref32) 2012
References_xml	– ident: ref18 doi: 10.1016/j.ress.2023.109319 – ident: ref3 doi: 10.1016/j.psep.2021.03.016 – ident: ref11 doi: 10.1016/j.jsv.2014.02.038 – ident: ref40 doi: 10.1109/ACCESS.2021.3065195 – ident: ref13 doi: 10.1016/j.ymssp.2023.110427 – ident: ref25 doi: 10.1109/TIM.2022.3168929 – ident: ref31 doi: 10.1109/TNNLS.2021.3059784 – ident: ref39 doi: 10.1088/1361-6501/ac3b0b – ident: ref41 doi: 10.3390/s22176570 – ident: ref19 doi: 10.1007/s00170-021-08126-8 – ident: ref15 doi: 10.1109/CVPR.2017.243 – ident: ref8 doi: 10.1021/ie300072q – year: 2017 ident: ref16 article-title: MobileNets: Efficient convolutional neural networks for mobile vision applications publication-title: arXiv:1704.04861 – ident: ref6 doi: 10.1214/aoms/1177704472 – ident: ref5 doi: 10.1016/j.isatra.2020.08.010 – volume: 12 start-page: 582 issue: 3 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref33 article-title: Support vector method for novelty detection – ident: ref21 doi: 10.1109/TIM.2021.3071232 – ident: ref37 doi: 10.1109/TIM.2022.3212542 – ident: ref36 doi: 10.1109/tevc.2023.3290172 – start-page: 6105 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref17 article-title: EfficientNet: Rethinking model scaling for convolutional neural networks – ident: ref24 doi: 10.1016/j.neucom.2022.04.111 – ident: ref1 doi: 10.1109/TIM.2019.2933119 – ident: ref38 doi: 10.3390/app112210889 – ident: ref12 doi: 10.4236/jcc.2014.29004 – ident: ref7 doi: 10.1155/2019/4031795 – ident: ref28 doi: 10.1109/TIE.2017.2752151 – ident: ref27 doi: 10.1109/TIM.2021.3072131 – ident: ref29 doi: 10.1109/ACCESS.2021.3097353 – start-page: 5 volume-title: Proc. Eur. Conf. Prognostics Health Manag. Soc. ident: ref2 article-title: Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification – ident: ref4 doi: 10.1016/j.jmsy.2023.07.012 – ident: ref22 doi: 10.1109/TIM.2021.3080402 – ident: ref10 doi: 10.1109/ICDM.2008.17 – ident: ref23 doi: 10.1016/j.jmsy.2021.03.022 – ident: ref34 doi: 10.1109/TIE.2017.2774777 – ident: ref26 doi: 10.1155/2021/1221462 – ident: ref20 doi: 10.1007/s11265-019-01463-8 – ident: ref14 doi: 10.1109/CVPR.2016.90 – ident: ref9 doi: 10.1109/TII.2012.2214394 – volume-title: Society for Machinery Failure Prevention Technology year: 2012 ident: ref32 – ident: ref30 doi: 10.1021/acs.iecr.9b03399 – ident: ref35 doi: 10.1109/TIM.2022.3188058
SSID	ssj0007647
Score	2.5100899
Snippet	Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Artificial neural networks Automatic architecture design bearing fault diagnosis (BFD) convolutional neural network (CNN) Convolutional neural networks Deep learning Fault diagnosis Feature extraction Floating point arithmetic genetic algorithm Genetic algorithms Lightweight Machine learning Mathematical analysis Rotating machinery Space exploration Tensors Vibrations
Title	Lightweight CNN Architecture Design Based on Spatial-Temporal Tensor and Its Application in Bearing Fault Diagnosis
URI	https://ieeexplore.ieee.org/document/10330715 https://www.proquest.com/docview/2904674231
Volume	73
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) 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/eLvHCXMwlV3NS8MwFA8qCnrwc-J0Sg5ePHTL2rRZjvNjKGjxMMVbSZNXGIxW1k7_fV_STiei4K2HvLT0l_eV90XIuZZKsBC4x0UqPG6E8lLbGdEwxXSm-kHmIrrP9yKOBy8v8rEpVne1MADgks-gax9dLN8Uem6vypDD0fsWtqR8VYioLtb6FLsi4nWDzD5yMJoFi5gkk73x3UPXjgnvBkGAGjj8poPcUJUfktipl9HOPz9sl2w3diQd1sDvkRXI98nWUnfBfbLhsjt1eUDKe-uCv7tbUHoVx3S4FD6g1y6Jg16iPjO0yKmdUoyn0hvXXaumdIyubjGjKjf0rirp8CvmTSdIh7yC76MjNZ9W9LpO3ZuULfI0uhlf3XrNtAVP-0xUnlLAhTbcBy2zNAt8ZgZSDWQY2mArMBOZiAEajL6JMqV1JlNlQCA_c3RzwQ8OyVpe5HBEKKAYFCyVnIHhka_QJAkhQ4IgMqHgUZv0Fv8_0U0rcjsRY5o4l4TJBBFLLGJJg1ibXHxSvNZtOP5Y27IILa2rwWmTzgLjpGHUMvEls_NW0Mo9_oXshGzi7ry-dumQtWo2h1Oyrt-qSTk7c2fwA_kr2Oc
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Nb9MwFH9CAwQcBoyhdQzmwy47pHMTJ66PZaNqtTbiEKbdIsd-kSpV6dSk49_n2Um3TmhI3HLwk638_L78vgDOjNKSxygCIQsZCCt1ULjOiJZrbko9iEof0b2ZyTQd3t6qn12xuq-FQUSffIZ99-lj-XZlNu6pjDicvG_pSspfxkKEvC3XehC8MhFti8wB8TAZBtuoJFcX2XTed4PC-1EUkQ6On2ghP1blL1nsFcz4_X8e7QPsd5YkG7XQf4QXWB3Au53-ggfw2ud3mvoT1DPnhP_276DsMk3ZaCeAwK58Ggf7ThrNslXF3JxiupdB1vatWrKMnN3VmunKsmlTs9Fj1JstiI64hfZjY71ZNuyqTd5b1Ifwa_wju5wE3byFwIRcNoHWKKSxIkSjyqKMQm6HSg9VHLtwK3Kb2IQjmYyhTUptTKkKbVESRwtydDGMPsNetarwCBiSIJS8UIKjFUmoySiJsSSCKLGxFEkPLrb_PzddM3I3E2OZe6eEq5wQyx1ieYdYD84fKO7aRhz_WHvoENpZ14LTg5MtxnnHqnUeKu4mrpCde_wM2Sm8mWTzWT6bptdf4C3tJNpHmBPYa9Yb_AqvzH2zqNff_H38A2mV3C4
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=Lightweight+CNN+Architecture+Design+Based+on+Spatial%E2%80%93Temporal+Tensor+and+Its+Application+in+Bearing+Fault+Diagnosis&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Wang%2C+Zan&rft.au=Lu%2C+Hui&rft.au=Shi%2C+Yuhui&rft.au=Wang%2C+Xianpeng&rft.date=2024&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=73&rft.spage=1&rft.epage=12&rft_id=info:doi/10.1109%2FTIM.2023.3336435&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIM_2023_3336435
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