Fault Diagnosis of Rotating Machinery Toward Unseen Working Condition: A Regularized Domain Adaptive Weight Optimization
Fault diagnosis under specific working conditions has achieved remarkable success. However, due to variations in working conditions, the assumption that training and test samples are independent and identically distributed is often violated, which makes the diagnostic model brittle under unseen work...
Saved in:
Published in | IEEE transactions on industrial informatics Vol. 20; no. 7; pp. 9130 - 9140 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.07.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Fault diagnosis under specific working conditions has achieved remarkable success. However, due to variations in working conditions, the assumption that training and test samples are independent and identically distributed is often violated, which makes the diagnostic model brittle under unseen working conditions. To this end, a generic generalization strategy, namely, regularized domain adaptive weight optimization strategy (RDAWOs), is devised for fault diagnosis of rotating machinery. We first design the architecture of a 1-D convolutional neural network. Then, the hyperparameter regularization term and an adaptive pooling layer are designed to control the complexity and improve the adaptability of the overparameterized deep model, respectively. Finally, domain adaptive weight optimization is established to identify the working condition abundant in spurious label-related information and to mine the robust fault knowledge under various working conditions. Obtained results indicate the strong generalization ability for out-of-distribution samples, as well as relatively high diagnostic accuracy of the RDAWOs-based deep model under unseen working conditions. |
---|---|
AbstractList | Fault diagnosis under specific working conditions has achieved remarkable success. However, due to variations in working conditions, the assumption that training and test samples are independent and identically distributed is often violated, which makes the diagnostic model brittle under unseen working conditions. To this end, a generic generalization strategy, namely, regularized domain adaptive weight optimization strategy (RDAWOs), is devised for fault diagnosis of rotating machinery. We first design the architecture of a 1-D convolutional neural network. Then, the hyperparameter regularization term and an adaptive pooling layer are designed to control the complexity and improve the adaptability of the overparameterized deep model, respectively. Finally, domain adaptive weight optimization is established to identify the working condition abundant in spurious label-related information and to mine the robust fault knowledge under various working conditions. Obtained results indicate the strong generalization ability for out-of-distribution samples, as well as relatively high diagnostic accuracy of the RDAWOs-based deep model under unseen working conditions. |
Author | Bo, Lin Su, Zuqiang Wang, Shuxian Tang, Zhi Honglin, Luo Luo, Maolin |
Author_xml | – sequence: 1 givenname: Zhi orcidid: 0000-0002-2028-3509 surname: Tang fullname: Tang, Zhi organization: School of Advance Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China – sequence: 2 givenname: Zuqiang orcidid: 0000-0002-2938-6213 surname: Su fullname: Su, Zuqiang email: suzq@cqupt.edu.cn organization: School of Advance Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China – sequence: 3 givenname: Shuxian orcidid: 0000-0002-0184-3021 surname: Wang fullname: Wang, Shuxian organization: School of Advance Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China – sequence: 4 givenname: Maolin orcidid: 0000-0002-5381-4695 surname: Luo fullname: Luo, Maolin organization: School of Advance Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China – sequence: 5 givenname: Luo orcidid: 0000-0003-3114-5686 surname: Honglin fullname: Honglin, Luo organization: Intelligent Manufacturing and Automobile School, Chongqing College of Electronic Engineering, Chongqing, China – sequence: 6 givenname: Lin orcidid: 0000-0002-5869-1591 surname: Bo fullname: Bo, Lin email: bolin0001@yahoo.com.cn organization: State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing, China |
BookMark | eNpNkMtLAzEQxoMoqNW7Bw8Bz1snj9003kp9FRRBKh6X6W7SRtukJlsf_etNqQdPM8N83zx-x2TfB28IOWPQZwz05WQ87nPgsi-E0pXke-SIackKgBL2c16WrBAcxCE5TukNQCgQ-oh83-J60dFrhzMfkks0WPocOuycn9FHbObOm_hDJ-ELY0tffDLG09cQ37f9UfCt61zwV3RIn81svcDoNqal12GJztNhi6vOfRr6atxs3tGnXC3dBreWE3JgcZHM6V_skZfbm8novnh4uhuPhg9Fw2XZFVNEbKpGyRzQGAOtZfmjCgbSQqOnSoMBjdZIZXnDrBhwUFUrm0qilq0VPXKxm7uK4WNtUle_hXX0eWUtQJWSV6oqswp2qiaGlKKx9Sq6JcafmkG95VtnvvWWb_3HN1vOdxaXz_onl7pUfCB-Aa5QeoY |
CODEN | ITIICH |
Cites_doi | 10.1109/TII.2021.3078712 10.1007/978-3-030-11220-2_8 10.1109/TII.2019.2917233 10.1016/j.neucom.2020.05.014 10.1016/j.neucom.2018.09.050 10.1016/j.sigpro.2019.03.019 10.1007/s10489-021-02504-1 10.5555/3045118.3045167 10.1109/TIM.2019.2956332 10.1109/TIM.2020.3016068 10.1016/j.measurement.2019.106906 10.1016/j.measurement.2022.110969 10.1016/j.ymssp.2020.107327 10.1109/ACCESS.2020.2994310 10.1007/978-3-319-49409-8_35 10.1007/s10489-020-02107-2 10.1007/s10845-020-01600-2 10.1609/aaai.v34i07.7003 10.1016/j.isatra.2019.08.012 10.1177/1077546313486284 10.1109/TETCI.2020.2972926 10.1088/1361-6501/abc6e3 10.1016/j.measurement.2019.02.073 10.1016/j.neucom.2017.02.045 10.1007/978-3-030-58536-5_8 10.1109/CVPR.2016.90 10.1016/j.ymssp.2022.108990 |
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 7SC 7SP 8FD JQ2 L7M L~C L~D |
DOI | 10.1109/TII.2024.3379642 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Explore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
DatabaseTitle | CrossRef 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 Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Technology Research Database |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 1941-0050 |
EndPage | 9140 |
ExternalDocumentID | 10_1109_TII_2024_3379642 10495728 |
Genre | orig-research |
GrantInformation_xml | – fundername: Science and Technology Research Project of Chongqing Education Commission grantid: KJQN202300628 – fundername: Chongqing Research Program of Technological Innovation and Application Demonstration grantid: CSTB2022TIAD-KPX0075 funderid: 10.13039/501100019070 – fundername: National Natural Science Foundation of China grantid: 52175077; 52205553 funderid: 10.13039/501100001809 – fundername: Key Development Projects of the Chengdu Science and Technology Plan grantid: 2023-YF11-00059-HZ |
GroupedDBID | 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ ABQJQ ABVLG ACGFS ACIWK AENEX AETIX AKJIK ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RIG RNS AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c245t-baaac6c74aacaeee0df10506084f0c9b790e09afe47f2c1f382076d4c64a94df3 |
IEDL.DBID | RIE |
ISSN | 1551-3203 |
IngestDate | Thu Oct 10 23:02:49 EDT 2024 Thu Aug 22 11:30:42 EDT 2024 Wed Jul 10 10:27:46 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | true |
Issue | 7 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c245t-baaac6c74aacaeee0df10506084f0c9b790e09afe47f2c1f382076d4c64a94df3 |
ORCID | 0000-0002-2028-3509 0000-0002-2938-6213 0000-0003-3114-5686 0000-0002-0184-3021 0000-0002-5381-4695 0000-0002-5869-1591 |
PQID | 3075426765 |
PQPubID | 85507 |
PageCount | 11 |
ParticipantIDs | ieee_primary_10495728 proquest_journals_3075426765 crossref_primary_10_1109_TII_2024_3379642 |
PublicationCentury | 2000 |
PublicationDate | 2024-07-01 |
PublicationDateYYYYMMDD | 2024-07-01 |
PublicationDate_xml | – month: 07 year: 2024 text: 2024-07-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE transactions on industrial informatics |
PublicationTitleAbbrev | TII |
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 ref12 ref15 ref14 ref11 ref10 (ref25) 2023 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref20 ref22 ref21 ref28 ref27 ref8 ref7 ref9 ref4 ref3 ref6 ref5 |
References_xml | – year: 2023 ident: ref25 article-title: The efforts for the interpretability of deep models – ident: ref17 doi: 10.1109/TII.2021.3078712 – ident: ref19 doi: 10.1007/978-3-030-11220-2_8 – ident: ref10 doi: 10.1109/TII.2019.2917233 – ident: ref18 doi: 10.1016/j.neucom.2020.05.014 – ident: ref21 doi: 10.1016/j.neucom.2018.09.050 – ident: ref6 doi: 10.1016/j.sigpro.2019.03.019 – ident: ref11 doi: 10.1007/s10489-021-02504-1 – ident: ref26 doi: 10.5555/3045118.3045167 – ident: ref5 doi: 10.1109/TIM.2019.2956332 – ident: ref22 doi: 10.1109/TIM.2020.3016068 – ident: ref9 doi: 10.1016/j.measurement.2019.106906 – ident: ref1 doi: 10.1016/j.measurement.2022.110969 – ident: ref2 doi: 10.1016/j.ymssp.2020.107327 – ident: ref24 doi: 10.1109/ACCESS.2020.2994310 – ident: ref27 doi: 10.1007/978-3-319-49409-8_35 – ident: ref12 doi: 10.1007/s10489-020-02107-2 – ident: ref4 doi: 10.1007/s10845-020-01600-2 – ident: ref14 doi: 10.1609/aaai.v34i07.7003 – ident: ref7 doi: 10.1016/j.isatra.2019.08.012 – ident: ref16 doi: 10.1177/1077546313486284 – ident: ref13 doi: 10.1109/TETCI.2020.2972926 – ident: ref20 doi: 10.1088/1361-6501/abc6e3 – ident: ref8 doi: 10.1016/j.measurement.2019.02.073 – ident: ref3 doi: 10.1016/j.neucom.2017.02.045 – ident: ref15 doi: 10.1007/978-3-030-58536-5_8 – ident: ref28 doi: 10.1109/CVPR.2016.90 – ident: ref23 doi: 10.1016/j.ymssp.2022.108990 |
SSID | ssj0037039 |
Score | 2.4465694 |
Snippet | Fault diagnosis under specific working conditions has achieved remarkable success. However, due to variations in working conditions, the assumption that... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 9130 |
SubjectTerms | Adaptation models Adaptive control Artificial neural networks Convolution Deep learning Diagnostic systems Effectiveness Employee welfare Fault diagnosis model generalization Optimization Regularization Rotating machinery Task analysis Training unseen working conditions Working conditions |
Title | Fault Diagnosis of Rotating Machinery Toward Unseen Working Condition: A Regularized Domain Adaptive Weight Optimization |
URI | https://ieeexplore.ieee.org/document/10495728 https://www.proquest.com/docview/3075426765 |
Volume | 20 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFA_qSQ9-i_OLHLx46MzaJG28DedwwibIht5KkiYy1Fa2DtS_3pe0BT8QPLWFtiR5L-_z914QOrWkI6nlOgD9ogJqOzJQiqnACpNoKpWgxsUhhyN-PaE3D-yhLlb3tTDGGA8-M21363P5WaEXLlQGOxzM-ThMltFyQsKqWKsRuxGwrvDNUVkniEISNTlJIs7HgwF4giFtR5GrvAy_6SB_qMovSezVS38DjZqBVaiSp_aiVG398aNn479HvonWa0MTdyvO2EJLJt9Ga1_aD-6gt75cPJe4V6HtpnNcWHxXuNx8_oiHHmVpZu947JG1eJLPwefFdXQdXxYu2Q1UvcBdfOdPtJ9NP0yGe8WLnOa4m8lXJ0rxvQ--4lt4eqmLPnfRpH81vrwO6pMYAh1SVgZKSqm5jilcJEyOZBbsMsJJQi3RQsWCGCKkNTS2oe7YCOyKmGdUcyoFzWy0h1byIjf7CHPgAlcOS01sqdUatCFLdMLjkEnNuGyhs4Y26WvVcCP1jgoRKdAxdXRMazq20K5b6i_vVavcQkcNNdN6S85TEGYMzJGYs4M_PjtEq-7vFRj3CK2Us4U5BpOjVCee1T4BbyzVYg |
link.rule.ids | 315,786,790,802,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3Nb9MwFH-CcQAOjI8hChv4wIVDipv4I-ZWbataWIs0tWK3yHbsqYIlU5tKsL-eZyeRBmgSpyRSoth-z-_79wzw3tORZl7YBPWLSZgf6cQYbhKvXG6ZNoq5EIecL8R0xT5f8IsOrB6xMM65WHzmhuE25vLL2u5CqAx3OJrzMs3vwwNU9FS2cK1e8GbIvCq2R-WjJEtp1mclqfq4nM3QF0zZMMsC9jL9QwvFY1X-kcVRwUz2YdEPra0r-T7cNWZob_7q2vjfY38KTzpTk4xb3ngG91z1HB7fakD4An5O9O5HQ07aerv1ltSenNchO19dknmss3SbX2QZa2vJqtqi10u6-Do5rkO6G-n6iYzJeTzTfrO-cSU5qa_0uiLjUl8HYUq-xfAr-YpPVx3s8wBWk9Pl8TTpzmJIbMp4kxittRVWMrxonBwtPVpmVNCceWqVkYo6qrR3TPrUjnyGloUUJbOCacVKn72Evaqu3CsgAvkgAGKZk555a1Ef8tzmQqZcWy70AD70tCmu25YbRXRVqCqQjkWgY9HRcQAHYalvvdeu8gAOe2oW3abcFijOOBokUvDXd3z2Dh5Ol_Oz4my2-PIGHoU_taW5h7DXbHbuCA2QxryNbPcb1J7Ytg |
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=Fault+Diagnosis+of+Rotating+Machinery+Toward+Unseen+Working+Condition%3A+A+Regularized+Domain+Adaptive+Weight+Optimization&rft.jtitle=IEEE+transactions+on+industrial+informatics&rft.au=Tang%2C+Zhi&rft.au=Su%2C+Zuqiang&rft.au=Wang%2C+Shuxian&rft.au=Luo%2C+Maolin&rft.date=2024-07-01&rft.issn=1551-3203&rft.eissn=1941-0050&rft.volume=20&rft.issue=7&rft.spage=9130&rft.epage=9140&rft_id=info:doi/10.1109%2FTII.2024.3379642&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TII_2024_3379642 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1551-3203&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1551-3203&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1551-3203&client=summon |