Deep Transfer Network With Multi-Kernel Dynamic Distribution Adaptation for Cross-Machine Fault Diagnosis

Recently, various deep learning models, which are mainly based on data-driven algorithms, have received more and more attention in the field of intelligent fault diagnosis and prognostics. However, there are two major assumptions accepted by default in the existing studies: 1) The training (source d...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 9; s. 16392 - 16409
Hlavní autori:	Lv, Mingzhu, Liu, Shixun, Su, Xiaoming, Chen, Changzheng
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Adaptation Algorithms Bearings Cognitive tasks cross-machine fault diagnosis Deep transfer network Diagnostic systems Domains Fault diagnosis Feature extraction Kernel Kernel functions Machine learning multi-kernel dynamic distribution adaptation Task analysis Testing Training transfer learning Vibrations Wind turbines
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Recently, various deep learning models, which are mainly based on data-driven algorithms, have received more and more attention in the field of intelligent fault diagnosis and prognostics. However, there are two major assumptions accepted by default in the existing studies: 1) The training (source domain) and testing (target domain) data sets obey the same feature distribution; 2) Sufficient labeled data with fault information is available for model training. In real industrial scenarios, especially for different machines, these assumptions are mostly invalid, which makes it a huge challenge to build reliable diagnostic model. Motivated by transfer learning, we present a novel intelligent method named deep transfer network (DTN) with multi-kernel dynamic distribution adaptation (MDDA) to address the problem of cross-machine fault diagnosis. In the proposed approach, the DTN has wide first-layer convolutional kernel and several small convolutional layers, which is utilized to extract transferable features across different machines and suppress high frequency noise. Then, the MDDA method constructs a weighted mixed kernel function to map different transferable features to a unified feature space, and the relative importance of the marginal and conditional distributions are also evaluated dynamically. The proposed method is verified by three transfer learning tasks of bearings, in which the health states of wind turbine bearings in real scenario are identified by using diagnosis knowledge from two different bearings in laboratories. The results show that the proposed method can achieve higher diagnosis accuracy and better transfer performance even under different noisy environment conditions than many other state-of-the-art methods. The presented framework offers a promising approach for cross-machine fault diagnosis.
AbstractList	Recently, various deep learning models, which are mainly based on data-driven algorithms, have received more and more attention in the field of intelligent fault diagnosis and prognostics. However, there are two major assumptions accepted by default in the existing studies: 1) The training (source domain) and testing (target domain) data sets obey the same feature distribution; 2) Sufficient labeled data with fault information is available for model training. In real industrial scenarios, especially for different machines, these assumptions are mostly invalid, which makes it a huge challenge to build reliable diagnostic model. Motivated by transfer learning, we present a novel intelligent method named deep transfer network (DTN) with multi-kernel dynamic distribution adaptation (MDDA) to address the problem of cross-machine fault diagnosis. In the proposed approach, the DTN has wide first-layer convolutional kernel and several small convolutional layers, which is utilized to extract transferable features across different machines and suppress high frequency noise. Then, the MDDA method constructs a weighted mixed kernel function to map different transferable features to a unified feature space, and the relative importance of the marginal and conditional distributions are also evaluated dynamically. The proposed method is verified by three transfer learning tasks of bearings, in which the health states of wind turbine bearings in real scenario are identified by using diagnosis knowledge from two different bearings in laboratories. The results show that the proposed method can achieve higher diagnosis accuracy and better transfer performance even under different noisy environment conditions than many other state-of-the-art methods. The presented framework offers a promising approach for cross-machine fault diagnosis.
Author	Chen, Changzheng Liu, Shixun Su, Xiaoming Lv, Mingzhu
Author_xml	– sequence: 1 givenname: Mingzhu orcidid: 0000-0002-0608-0852 surname: Lv fullname: Lv, Mingzhu email: zhaogx@sut.edu.cn organization: School of Mechanical Engineering, Shenyang University of Technology, Shenyang, China – sequence: 2 givenname: Shixun orcidid: 0000-0002-7739-0874 surname: Liu fullname: Liu, Shixun organization: School of Mechanical Engineering, Shenyang University of Technology, Shenyang, China – sequence: 3 givenname: Xiaoming orcidid: 0000-0003-0391-2278 surname: Su fullname: Su, Xiaoming organization: School of Mechanical Engineering, Shenyang University of Technology, Shenyang, China – sequence: 4 givenname: Changzheng orcidid: 0000-0002-7874-8399 surname: Chen fullname: Chen, Changzheng organization: School of Mechanical Engineering, Shenyang University of Technology, Shenyang, China
BookMark	eNqFUU1P3DAQjSoqlVJ-AZdIPWfrjyS2j6ssUFRoD1D1aI2dCXgb7K3tVcW_r5cgVPVSXzx6fu_NeN776sgHj1V1RsmKUqI-rYfh_PZ2xQijK046TkT3pjpmtFcN73h_9Ff9rjpNaUvKkQXqxHHlNoi7-i6CTxPG-ivm3yH-rH-4_FDf7Ofsmi8YPc715snDo7P1xqUcndlnF3y9HmGX4bmcQqyHGFJqbsA-OI_1BRR94cO9D8mlD9XbCeaEpy_3SfX94vxu-Nxcf7u8GtbXjW2JzI0yyhghiBQjt9BPbDKGFUhOsseRslH0hkCHreRTx6RUtJXYwwiKEQ6d4SfV1eI7BtjqXXSPEJ90AKefgRDvNcTs7IzaUNF2YHvKrWxHAZIKKQiVlDFsqWXF6-PitYvh1x5T1tuwj76Mr1kZgJWVqr6w-MKyh_9HnF67UqIPEeklIn2ISL9EVFTqH5V1yy5zBDf_R3u2aB0ivnZTnElRXv8AvCaggw
CODEN	IAECCG
CitedBy_id	crossref_primary_10_3233_JIFS_213340 crossref_primary_10_1109_JSEN_2024_3356605 crossref_primary_10_1016_j_measurement_2022_111996 crossref_primary_10_1080_0952813X_2023_2241867 crossref_primary_10_1177_01423312231157118 crossref_primary_10_1088_1361_6501_ad4380 crossref_primary_10_1016_j_ymssp_2021_108487 crossref_primary_10_1109_ACCESS_2023_3239784 crossref_primary_10_1007_s12206_023_0306_z crossref_primary_10_1016_j_psep_2025_107885 crossref_primary_10_1109_TIM_2022_3157007 crossref_primary_10_1088_1361_6501_ac99f4 crossref_primary_10_1016_j_psep_2024_06_060 crossref_primary_10_1109_ACCESS_2022_3205105 crossref_primary_10_1109_TIM_2023_3308251 crossref_primary_10_1016_j_knosys_2023_111158 crossref_primary_10_1007_s13369_023_07810_z crossref_primary_10_1016_j_cja_2021_10_006
Cites_doi	10.1016/j.patrec.2020.06.007 10.1177/1748006X19867776 10.1109/ACCESS.2020.3020906 10.3390/s17020425 10.1016/j.jkss.2019.05.005 10.3390/s20010234 10.1109/TGRS.2017.2692281 10.1109/TIE.2017.2777383 10.1016/j.cja.2019.07.011 10.1109/TR.2019.2896240 10.1016/j.ymssp.2018.12.051 10.3390/s20051361 10.1016/j.ymssp.2017.11.016 10.3390/ma10060574 10.1016/j.advwatres.2016.05.005 10.1007/s00500-019-04038-8 10.1109/TIE.2016.2627020 10.1016/j.tcs.2018.06.004 10.1016/j.measurement.2019.02.073 10.1016/j.ress.2020.107050 10.1109/TR.2015.2456056 10.1109/JSEN.2019.2936932 10.1002/we.2510 10.1016/j.neunet.2020.01.009 10.1007/s11071-019-05176-2 10.1145/3360309 10.1109/TGRS.2020.2985072 10.1016/j.neucom.2019.12.033 10.1016/j.isatra.2019.08.012 10.1109/TGRS.2019.2928562 10.1109/TIE.2016.2582729 10.1109/TIP.2017.2651375 10.1109/TII.2018.2869429
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2021.3053075
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	16409
ExternalDocumentID	oai_doaj_org_article_b1745ac613c84d7a81787018122e41c2 10_1109_ACCESS_2021_3053075 9328775
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 51675350 funderid: 10.13039/501100001809
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c408t-9b9bb77087d3ca6f2fbb29bb8f86ed12d76b0a5e483f52889148e6ada9203a5b3
IEDL.DBID	RIE
ISICitedReferencesCount	20
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000613542000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:40:15 EDT 2025 Sun Nov 30 05:02:34 EST 2025 Sat Nov 29 06:11:53 EST 2025 Tue Nov 18 21:22:39 EST 2025 Wed Aug 27 05:54:23 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c408t-9b9bb77087d3ca6f2fbb29bb8f86ed12d76b0a5e483f52889148e6ada9203a5b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-0391-2278 0000-0002-7739-0874 0000-0002-7874-8399 0000-0002-0608-0852
OpenAccessLink	https://ieeexplore.ieee.org/document/9328775
PQID	2483253696
PQPubID	4845423
PageCount	18
ParticipantIDs	doaj_primary_oai_doaj_org_article_b1745ac613c84d7a81787018122e41c2 proquest_journals_2483253696 crossref_primary_10_1109_ACCESS_2021_3053075 crossref_citationtrail_10_1109_ACCESS_2021_3053075 ieee_primary_9328775
PublicationCentury	2000
PublicationDate	20210000 2021-00-00 20210101 2021-01-01
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– year: 2021 text: 20210000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2021
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 ref33 ref11 ref32 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: ref17 doi: 10.1016/j.patrec.2020.06.007 – ident: ref7 doi: 10.1177/1748006X19867776 – ident: ref31 doi: 10.1109/ACCESS.2020.3020906 – ident: ref10 doi: 10.3390/s17020425 – ident: ref16 doi: 10.1016/j.jkss.2019.05.005 – ident: ref25 doi: 10.3390/s20010234 – ident: ref28 doi: 10.1109/TGRS.2017.2692281 – ident: ref21 doi: 10.1109/TIE.2017.2777383 – ident: ref26 doi: 10.1016/j.cja.2019.07.011 – ident: ref29 doi: 10.1109/TR.2019.2896240 – ident: ref11 doi: 10.1016/j.ymssp.2018.12.051 – ident: ref30 doi: 10.3390/s20051361 – ident: ref1 doi: 10.1016/j.ymssp.2017.11.016 – ident: ref33 doi: 10.3390/ma10060574 – ident: ref15 doi: 10.1016/j.advwatres.2016.05.005 – ident: ref20 doi: 10.1007/s00500-019-04038-8 – ident: ref3 doi: 10.1109/TIE.2016.2627020 – ident: ref14 doi: 10.1016/j.tcs.2018.06.004 – ident: ref9 doi: 10.1016/j.measurement.2019.02.073 – ident: ref12 doi: 10.1016/j.ress.2020.107050 – ident: ref5 doi: 10.1109/TR.2015.2456056 – ident: ref8 doi: 10.1109/JSEN.2019.2936932 – ident: ref13 doi: 10.1002/we.2510 – ident: ref24 doi: 10.1016/j.neunet.2020.01.009 – ident: ref4 doi: 10.1007/s11071-019-05176-2 – ident: ref19 doi: 10.1145/3360309 – ident: ref18 doi: 10.1109/TGRS.2020.2985072 – ident: ref2 doi: 10.1016/j.neucom.2019.12.033 – ident: ref23 doi: 10.1016/j.isatra.2019.08.012 – ident: ref32 doi: 10.1109/TGRS.2019.2928562 – ident: ref27 doi: 10.1109/TIE.2016.2582729 – ident: ref22 doi: 10.1109/TIP.2017.2651375 – ident: ref6 doi: 10.1109/TII.2018.2869429
SSID	ssj0000816957
Score	2.3119798
Snippet	Recently, various deep learning models, which are mainly based on data-driven algorithms, have received more and more attention in the field of intelligent...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	16392
SubjectTerms	Adaptation Algorithms Bearings Cognitive tasks cross-machine fault diagnosis Deep transfer network Diagnostic systems Domains Fault diagnosis Feature extraction Kernel Kernel functions Machine learning multi-kernel dynamic distribution adaptation Task analysis Testing Training transfer learning Vibrations Wind turbines
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA4iHvQgahWrVXLw6Go2-0hyrK1FEIsHxd5CXosFqaWt_n4nj5aKoBev2SSbzMxmZnZnvw-hC2VKXjR5mRW6NFnJuIZzUNuMVEopoTVcagLZBBsO-WgkHteovnxNWIQHjoK71hAyV8qA1zG8tEzx3JuY90vUlbkJpy9hYi2ZCmcwz2tRsQQzlBNx3e31YEeQENL8CmwcTLv65ooCYn-iWPlxLgdnM9hDuylKxN24un204SYHaGcNO7CFxn3npji4msbN8DCWc-OX8eIVh79qs3s3m7g33I-c87jvIXITuxXuWjWNH-ExRK245xeYPYTCSocHCsZD_1CEN54foufB7VPvLku8CZkpCV9kQoOQGSOc2cKouqGN1hSaeMNrZ3NqWa2JqpzXUkU5F5ASuVpZJSgpVKWLI7Q5eZ-4Y4QLCFCs5oZayDs4EdrDCSrLeFkwC7llG9GlCKVJoOKe2-JNhuSCCBnlLr3cZZJ7G12uBk0jpsbv3W-8blZdPSB2aAAzkclM5F9m0kYtr9nVJBC2cubn7iw1LdPDO5cUBEMrT3R48h-3PkXbfjvxvU0HbS5mH-4MbZnPxXg-Ow92-wXBAOyY priority: 102 providerName: Directory of Open Access Journals
Title	Deep Transfer Network With Multi-Kernel Dynamic Distribution Adaptation for Cross-Machine Fault Diagnosis
URI	https://ieeexplore.ieee.org/document/9328775 https://www.proquest.com/docview/2483253696 https://doaj.org/article/b1745ac613c84d7a81787018122e41c2
Volume	9
WOSCitedRecordID	wos000613542000001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Na9wwEB2SkEN7aJukpdumQYce48SWLUs6bnezFEKWHFqSm9DHmC6EzbK76bG_vSNZMS0pgV6MkSUj6Y2kGWn0BuCz9Y2qu6opatf4opHK0TzoQlEKa612jj51KdiEnM_V7a2-3oHT4S4MIibnMzyLr-ksP9z7h7hVdk66hpJS7MKulG1_V2vYT4kBJLSQmVioKvX5eDKhNpAJyKszkmoSZvHX4pM4-nNQlSczcVpeZq__r2Jv4FVWI9m4x_0AdnB5CC__IBc8gsUUccXSWtThms17f292s9j-YOnabXGJ6yXesWkflJ5NI4duDn_FxsGu-lN6Rmotm8T2FFfJ8xLZzFJ5yp-89Babt_B9dvFt8rXIgRUK35RqW2hHKEhZKhlqb9uOd85xSlKdajFUPMjWlVZghFFwpTTZTNjaYDUvaytc_Q72lvdLfA-sJg0mOOV5IMNEldpFvkEbpGpqGcj4HAF_7HHjM-t4DH5xZ5L1UWrTw2QiTCbDNILTodCqJ914PvuXCOWQNTJmpwTCyOQBaByZXsJ60l68aoK0qopTVdRvODaV5yM4irgOP8mQjuD4UTBMHt0bw6ljuIiRED_8u9RHeBEr2G_VHMPedv2An2Df_9wuNuuTZPfT8-rXxUkS4t8pre1p
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LbxMxEB6VggQ9lEdBpC3gA8du6_XasX0MCVFR24hDEb1Zfq0aqUqjJO3v79jrrkAgJG4rr71a-_Njxh5_H8Bn67lq2ppXjeO-4lI5nAddqKiw1mrn8FWbxSbkbKaurvT3LTjq78LEGHPwWTxOj_ksP9z6u7RVdoK2hpJSPIGngnNGu9ta_Y5KkpDQQhZqoZrqk9F4jLVAJ5DVx9ivsTuL35afzNJfZFX-mIvzAjN9-X-_9gp2iyFJRh3yr2ErLt7Azi_0gnswn8S4JHk1auOKzLqIb_Jzvrkm-eJtdRZXi3hDJp0sPZkkFt0igEVGwS67c3qChi0Zp_pUFzn2MpKpxfKYP8fpzddv4cf06-X4tCrSCpXnVG0q7RAHKamSofF22LLWOYZJqlXDGGoW5NBRK2ICUjClNHpNcWiD1Yw2VrjmHWwvbhfxPZAGbZjglGcBXRNFtUuMgzZIxRsZ0P0cAHtsceML73iSv7gx2f-g2nQwmQSTKTAN4KgvtOxoN_6d_UuCss-aOLNzAmJkyhA0Dp0vYT3aL17xIK2q02SVLBwWee3ZAPYSrv1HCqQDOHzsGKaM77Vh2DBMJC3E_b-X-gTPTy8vzs35t9nZAbxIP9tt3BzC9mZ1Fz_AM3-_ma9XH3MnfgB2pu6K
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=Deep+Transfer+Network+With+Multi-Kernel+Dynamic+Distribution+Adaptation+for+Cross-Machine+Fault+Diagnosis&rft.jtitle=IEEE+access&rft.au=Lv%2C+Mingzhu&rft.au=Liu%2C+Shixun&rft.au=Su%2C+Xiaoming&rft.au=Chen%2C+Changzheng&rft.date=2021&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=9&rft.spage=16392&rft.epage=16409&rft_id=info:doi/10.1109%2FACCESS.2021.3053075&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2021_3053075
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon