Sparse Representation Convolutional Autoencoder for Feature Learning of Vibration Signals and its Applications in Machinery Fault Diagnosis

Vibration signals are widely utilized in many fields, which can reflect machine health state. Those typical deep learning techniques cannot learn impulsive features from vibration signals due to interference of strong background noise. Supervised learning greatly rely on vast labeled data, which lim...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on industrial electronics (1982) Jg. 69; H. 12; S. 13565 - 13575
Hauptverfasser: Miao, Mengqi, Sun, Yuanhang, Yu, Jianbo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:0278-0046, 1557-9948
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Vibration signals are widely utilized in many fields, which can reflect machine health state. Those typical deep learning techniques cannot learn impulsive features from vibration signals due to interference of strong background noise. Supervised learning greatly rely on vast labeled data, which limits the implementation of deep learning in industry applications. Hence, in this article, a new deep neural network (DNN), sparse representation convolutional autoencoder (SRCAE), is proposed to extract impulsive components of vibration signals for machinery fault diagnosis in an unsupervised manner. A sparse representation (SR) block is proposed to extract impulsive components of vibration signals and transform the time-domain signal to a sparse domain by sparse mapping of a convolutional graph. The SR block is inserted into a deep network to remove noise and learn impulsive features for machinery fault diagnosis. Furthermore, an unsupervised selective feature transmission mechanism is proposed to improve training efficiency and realize feature filtering simultaneously. Finally, the effectiveness of SRCAE is verified on rotary machine fault diagnosis experiments. The testing results show that SRCAE has good noise filtering and impulsive components extraction performance. The recognition accuracy of SRCAE reached 97.16% based on the fivefold cross validation, which demonstrates the outperformance of SRCAE in comparison with state-of-the-art DNNs.
AbstractList Vibration signals are widely utilized in many fields, which can reflect machine health state. Those typical deep learning techniques cannot learn impulsive features from vibration signals due to interference of strong background noise. Supervised learning greatly rely on vast labeled data, which limits the implementation of deep learning in industry applications. Hence, in this article, a new deep neural network (DNN), sparse representation convolutional autoencoder (SRCAE), is proposed to extract impulsive components of vibration signals for machinery fault diagnosis in an unsupervised manner. A sparse representation (SR) block is proposed to extract impulsive components of vibration signals and transform the time-domain signal to a sparse domain by sparse mapping of a convolutional graph. The SR block is inserted into a deep network to remove noise and learn impulsive features for machinery fault diagnosis. Furthermore, an unsupervised selective feature transmission mechanism is proposed to improve training efficiency and realize feature filtering simultaneously. Finally, the effectiveness of SRCAE is verified on rotary machine fault diagnosis experiments. The testing results show that SRCAE has good noise filtering and impulsive components extraction performance. The recognition accuracy of SRCAE reached 97.16% based on the fivefold cross validation, which demonstrates the outperformance of SRCAE in comparison with state-of-the-art DNNs.
Author Miao, Mengqi
Sun, Yuanhang
Yu, Jianbo
Author_xml – sequence: 1
  givenname: Mengqi
  surname: Miao
  fullname: Miao, Mengqi
  email: 2011188@tongji.edu.cn
  organization: School of Mechanical Engineering, Tongji University, Shanghai, China
– sequence: 2
  givenname: Yuanhang
  surname: Sun
  fullname: Sun, Yuanhang
  email: 1710223@tongji.edu.cn
  organization: School of Mechanical Engineering, Tongji University, Shanghai, China
– sequence: 3
  givenname: Jianbo
  orcidid: 0000-0003-3204-2486
  surname: Yu
  fullname: Yu, Jianbo
  email: jbyu@tongji.edu.cn
  organization: School of Mechanical Engineering, Tongji University, Shanghai, China
BookMark eNp9kMFq3DAQhkVIIZu090Iugp69lWTLso7LJtsGthSatFczOzveKLiSK8mBfYa-dL116KGHXGYG5v-G4btk5z54Yuy9FEsphf34cHe7VELJZSlV01h9xhZSa1NYWzXnbCGUaQohqvqCXab0JISstNQL9vt-gJiIf6MhUiKfIbvg-Tr459CPpxl6vhpzII9hT5F3IfINQR4j8S1B9M4feOj4D7eLM3vvDhOUOPg9dznx1TD0Dv_uEneefwF8dJ7ikW9g7DO_cXDwIbn0lr3pJpDevfQr9n1z-7D-XGy_frpbr7YFKitzYfaAHaBBVZkaYSqdLhFFbcqOBNhdJaVCS1KSFbud7iqDiBZ1aaCRCOUV-zDfHWL4NVLK7VMY4-nnVtVNY4RU2kypek5hDClF6lp0s50cwfWtFO1JfDuJb0_i2xfxEyj-A4fofkI8voZcz4gjon9xW09_mKb8A2URk5I
CODEN ITIED6
CitedBy_id crossref_primary_10_1016_j_measurement_2022_112345
crossref_primary_10_1109_TII_2023_3254601
crossref_primary_10_1016_j_asoc_2024_111594
crossref_primary_10_3390_s23031305
crossref_primary_10_3390_s24216813
crossref_primary_10_1088_1361_6501_acf2b1
crossref_primary_10_1016_j_ress_2023_109601
crossref_primary_10_1016_j_ymssp_2023_110789
crossref_primary_10_1109_TMECH_2022_3191051
crossref_primary_10_1016_j_ress_2024_110347
crossref_primary_10_3390_s25102959
crossref_primary_10_1007_s10845_023_02160_x
crossref_primary_10_1016_j_neucom_2025_130934
crossref_primary_10_1016_j_ymssp_2024_111331
crossref_primary_10_1016_j_eswa_2023_122393
crossref_primary_10_1016_j_ymssp_2025_113271
crossref_primary_10_1109_TII_2022_3188507
crossref_primary_10_1016_j_measurement_2024_115608
crossref_primary_10_3390_machines12020127
crossref_primary_10_1016_j_ymssp_2023_110678
crossref_primary_10_3390_app15147698
crossref_primary_10_1109_TII_2025_3529924
crossref_primary_10_1109_TIM_2023_3320730
crossref_primary_10_1007_s13042_023_01934_2
crossref_primary_10_1088_1361_6501_ad356e
crossref_primary_10_1109_ACCESS_2023_3247430
crossref_primary_10_1109_TASE_2023_3260281
crossref_primary_10_1016_j_ress_2023_109795
crossref_primary_10_1109_JIOT_2024_3395331
Cites_doi 10.1109/TIM.2020.3011734
10.1016/j.neunet.2020.08.008
10.1109/TIE.2020.2994868
10.1109/JSEN.2019.2949057
10.1016/j.ymssp.2020.106740
10.1109/JSTSP.2007.910971
10.1109/TII.2017.2662215
10.1109/TIE.2020.2972458
10.1109/TSMC.2017.2754287
10.1109/CVPR.2015.7298681
10.1109/TIM.2020.3039612
10.1109/TII.2020.2966326
10.1109/TSMC.2016.2625840
10.1016/j.isprsjprs.2017.05.001
10.1109/TNNLS.2020.2966744
10.1016/j.ymssp.2017.09.028
10.1109/TIE.2018.2838070
10.1088/1361-6501/abcefb
10.1016/j.sigpro.2013.04.018
10.1016/j.ymssp.2006.06.010
10.1109/MMSP48831.2020.9287107
10.1088/1361-6501/abb917
10.1109/TIE.2017.2774777
10.1109/TSMC.2018.2850367
10.1109/TIE.2019.2912763
10.1109/TIE.2020.2973894
10.1109/TNNLS.2013.2280280
10.1109/TSMC.2016.2637279
10.1109/CVPR.2016.90
10.1016/j.neucom.2018.06.078
10.1109/TIM.2021.3105252
10.1109/TIM.2020.3047922
10.1109/TII.2020.2967822
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/TIE.2021.3128895
DatabaseName IEEE Xplore (IEEE)
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1557-9948
EndPage 13575
ExternalDocumentID 10_1109_TIE_2021_3128895
9625778
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 71777173
  funderid: 10.13039/501100001809
– fundername: Action Plan for Scientific and Technological Innovation of Shanghai Science and Technology Commission
  grantid: 21SQBS01402
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
5VS
6IK
97E
9M8
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACKIV
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
HZ~
H~9
IBMZZ
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
TWZ
VH1
VJK
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c291t-7dacfac7c2476ca476f53cc0673fe0a9b4112c9e11e90bb5f47ccc9c537a81ca3
IEDL.DBID RIE
ISICitedReferencesCount 35
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000838702800023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0278-0046
IngestDate Mon Jun 30 10:20:44 EDT 2025
Sat Nov 29 01:31:54 EST 2025
Tue Nov 18 21:18:39 EST 2025
Wed Aug 27 02:14:01 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 12
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-c291t-7dacfac7c2476ca476f53cc0673fe0a9b4112c9e11e90bb5f47ccc9c537a81ca3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-3204-2486
PQID 2688701257
PQPubID 85464
PageCount 11
ParticipantIDs crossref_citationtrail_10_1109_TIE_2021_3128895
crossref_primary_10_1109_TIE_2021_3128895
proquest_journals_2688701257
ieee_primary_9625778
PublicationCentury 2000
PublicationDate 2022-12-01
PublicationDateYYYYMMDD 2022-12-01
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-12-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on industrial electronics (1982)
PublicationTitleAbbrev TIE
PublicationYear 2022
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
ref14
ref31
ref30
ref11
ref10
ref32
ref2
ref1
ref17
ref16
ref38
ref19
ref18
Loparo (ref37) 2015
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref22
  doi: 10.1109/TIM.2020.3011734
– ident: ref13
  doi: 10.1016/j.neunet.2020.08.008
– ident: ref3
  doi: 10.1109/TIE.2020.2994868
– ident: ref38
  doi: 10.1109/JSEN.2019.2949057
– ident: ref15
  doi: 10.1016/j.ymssp.2020.106740
– ident: ref27
  doi: 10.1109/JSTSP.2007.910971
– ident: ref32
  doi: 10.1109/TII.2017.2662215
– ident: ref17
  doi: 10.1109/TIE.2020.2972458
– ident: ref23
  doi: 10.1109/TII.2017.2662215
– ident: ref19
  doi: 10.1109/TSMC.2017.2754287
– ident: ref30
  doi: 10.1109/CVPR.2015.7298681
– ident: ref16
  doi: 10.1109/TIM.2020.3039612
– ident: ref34
  doi: 10.1109/TII.2020.2966326
– ident: ref24
  doi: 10.1109/TSMC.2016.2625840
– year: 2015
  ident: ref37
  article-title: Bearings vibration data set,
– ident: ref29
  doi: 10.1016/j.isprsjprs.2017.05.001
– ident: ref7
  doi: 10.1109/TNNLS.2020.2966744
– ident: ref26
  doi: 10.1016/j.ymssp.2017.09.028
– ident: ref25
  doi: 10.1109/TIE.2018.2838070
– ident: ref35
  doi: 10.1088/1361-6501/abcefb
– ident: ref28
  doi: 10.1016/j.sigpro.2013.04.018
– ident: ref2
  doi: 10.1016/j.ymssp.2006.06.010
– ident: ref31
  doi: 10.1109/MMSP48831.2020.9287107
– ident: ref18
  doi: 10.1088/1361-6501/abb917
– ident: ref9
  doi: 10.1109/TIE.2017.2774777
– ident: ref12
  doi: 10.1088/1361-6501/abcefb
– ident: ref6
  doi: 10.1109/TSMC.2018.2850367
– ident: ref8
  doi: 10.1109/TIE.2019.2912763
– ident: ref1
  doi: 10.1109/TIE.2020.2973894
– ident: ref4
  doi: 10.1109/TNNLS.2013.2280280
– ident: ref20
  doi: 10.1109/TSMC.2016.2637279
– ident: ref14
  doi: 10.1109/CVPR.2016.90
– ident: ref5
  doi: 10.1016/j.neucom.2018.06.078
– ident: ref11
  doi: 10.1109/TIM.2021.3105252
– ident: ref10
  doi: 10.1109/TIM.2020.3047922
– ident: ref21
  doi: 10.1109/TII.2020.2967822
SSID ssj0014515
Score 2.547645
Snippet Vibration signals are widely utilized in many fields, which can reflect machine health state. Those typical deep learning techniques cannot learn impulsive...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 13565
SubjectTerms Artificial neural networks
Background noise
Convolution
Convolutional autoencoder
Deep learning
Fault diagnosis
Feature extraction
Filtering
Filtration
Industrial applications
Machine learning
Machinery
machinery fault diagnosis
Representations
Rotary machines
selective residual learning
sparse representation (SR)
Training
Vibration
Vibrations
Title Sparse Representation Convolutional Autoencoder for Feature Learning of Vibration Signals and its Applications in Machinery Fault Diagnosis
URI https://ieeexplore.ieee.org/document/9625778
https://www.proquest.com/docview/2688701257
Volume 69
WOSCitedRecordID wos000838702800023&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 Electronic Library (IEL)
  customDbUrl:
  eissn: 1557-9948
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014515
  issn: 0278-0046
  databaseCode: RIE
  dateStart: 19820101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Na9wwEBVJyKE9tEnT0k2TokMvhbprS7YlHUOaJT0khCYtuRl5PA6GYAevHehv6J_OSNYuCy2FXIyNNcbwZOk9zxdjn2ye5CVKGckYSKBYiZHVFV0aNFBqTfdq32xCXV7q21tztcW-rHNhENEHn-FXd-p9-VUHo_tVNjdE1pXS22xbqXzK1Vp7DNJs6lYgXMVYEn0rl2Rs5jffz0gIioT0qdDadZLY2IJ8T5W_FmK_uyxeP--99tirwCL5yQT7PtvC9g17uVFb8ID9uX4gzYr8hw91DRlGLT_t2scw29wDxqFzlSwr7DmxV-4I4dgjD1VX73hX819OUHvb6-bOVVvmtq14Myz5yYbzmzctv_CBmdj_5gs73g_82xTG1yzfsp-Ls5vT8yh0XohAmGSIVGWhtqBApCoHS4c6kwCuqU2NsTVlSjQNDCYJmrgsszpVAGAgk8rqBKx8x3barsX3jEslZF2RbMRMpFalGo0mUkEyjZgT6njG5iswCghlyV13jPvCy5PYFARf4eArAnwz9nlt8TCV5PjP2AMH13pcQGrGjlZ4F-GbXRYipwWX9utMHf7b6gN7IVzygwtmyY7YztCPeMx24XFolv1HPx2fAGYh38g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1da9RAFL3UKmgf_KriatV58EUwbjKT7Mw8ltqlxXYRu0rfwmRyUwIlKdmk0N_gn_bOZHZZUARfQkLmhsCZzJyT-wXwwcySWYFCRCK2JFCMwMioki41alsoRfcq32xCLhbq8lJ_24FPm1wYRPTBZ_jZnXpfftnawf0qm2oi61Kqe3A_S1Mej9laG59Bmo39CrirGUuyb-2UjPV0eXpMUpAnpFC5Uq6XxNYm5Luq_LEU-_1l_uT_3uwpPA48kh2OwD-DHWyew95WdcF9-HVxQ6oV2Xcf7BpyjBp21Da3Yb65Bwx962pZltgx4q_MUcKhQxbqrl6xtmI_naT2thf1lau3zExTsrpfscMt9zerG3buQzOxu2NzM1z37MsYyFevXsCP-fHy6CQKvRciy3XSR7I0tjJWWp7KmTV0qDJhrWtrU2FsdJESUbMakwR1XBRZlUprrbaZkEYl1oiXsNu0Db4CJiQXVUnCETOeGpkq1IpoBQk14k6o4glM12DkNhQmd_0xrnMvUGKdE3y5gy8P8E3g48biZizK8Y-x-w6uzbiA1AQO1njn4atd5XxGSy7t2Jl8_Xer9_DwZHl-lp-dLr6-gUfcpUL40JYD2O27Ad_CA3vb16vunZ-avwEs0uML
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=Sparse+Representation+Convolutional+Autoencoder+for+Feature+Learning+of+Vibration+Signals+and+its+Applications+in+Machinery+Fault+Diagnosis&rft.jtitle=IEEE+transactions+on+industrial+electronics+%281982%29&rft.au=Miao%2C+Mengqi&rft.au=Sun%2C+Yuanhang&rft.au=Yu%2C+Jianbo&rft.date=2022-12-01&rft.issn=0278-0046&rft.eissn=1557-9948&rft.volume=69&rft.issue=12&rft.spage=13565&rft.epage=13575&rft_id=info:doi/10.1109%2FTIE.2021.3128895&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIE_2021_3128895
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0046&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0046&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0046&client=summon