A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data
Low-quality data, including insufficient samples and low signal to noise ratio (SNR), restrict the effective application of intelligent diagnostic methods based on deep learning. In this study, a new rolling bearing enhanced diagnostic method is proposed based on swin-transformer (SWT) and ReliefF (...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on instrumentation and measurement 2024-01, Vol.73, p.1-1 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE transactions on instrumentation and measurement |
| container_volume | 73 |
| creator | Chen, Jiayu Lin, Cuiying Lu, Qinhua Yang, Chaoqi Li, Peng Yu, Pingchao Ge, Hongjuan |
| description | Low-quality data, including insufficient samples and low signal to noise ratio (SNR), restrict the effective application of intelligent diagnostic methods based on deep learning. In this study, a new rolling bearing enhanced diagnostic method is proposed based on swin-transformer (SWT) and ReliefF (RF) combined with Dempster-Shafer (DS) evidence theory. First, SWT is improved for adaptive deep feature mining of the vibration signal. Meanwhile, to enhance the quality of features, RF is introduced to optimize the deep fault features output by the global average pooling layer, which helps improve the classifier performance. Then, the DS evidence theory-based decision fusion strategy is designed to realize the fusion of different axial signals at the decision level, which enhances fault knowledge threshold and further improves the diagnostic ability. Finally, the bearing cases with data collected from the accelerated life degradation and different distributions are studied. The results reveal that the proposed method can adaptively mine fault features with low-quality data and realize efficient enhance diagnosis. |
| doi_str_mv | 10.1109/TIM.2024.3350130 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2920297603</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10381887</ieee_id><sourcerecordid>2920297603</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-ef48be07c8e4b7845953c55e9b1763015b508678c56182c05b34c2b66cff6d4b3</originalsourceid><addsrcrecordid>eNpNkDtPwzAYRS0EEqWwMzBYYk75HD8zlj6gUiukUsSEIsdx2lQhbu1EqP-elHZgusu590oHoXsCA0IgeVrNFoMYYjaglAOhcIF6hHMZJULEl6gHQFSUMC6u0U0IWwCQgske-hrisTVlKF2Np-1fvH-uouUUL2yzcTkunMdLV1VlvcbPVvtjTuqNro3N8bjU69qFMuC2zq3Hc_cT7Vtdlc0Bj3Wjb9FVoatg787ZRx_TyWr0Gs3fXmaj4TwycRI3kS2YyixIoyzLpGI84dRwbpOMSEGB8IyDElIZLoiKDfCMMhNnQpiiEDnLaB89nnZ33u1bG5p061pfd5dpdwBxIgXQjoITZbwLwdsi3fnyW_tDSiA9Skw7ielRYnqW2FUeTpXSWvsPp4ooJekvHeZryA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2920297603</pqid></control><display><type>article</type><title>A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data</title><source>IEEE Electronic Library (IEL)</source><creator>Chen, Jiayu ; Lin, Cuiying ; Lu, Qinhua ; Yang, Chaoqi ; Li, Peng ; Yu, Pingchao ; Ge, Hongjuan</creator><creatorcontrib>Chen, Jiayu ; Lin, Cuiying ; Lu, Qinhua ; Yang, Chaoqi ; Li, Peng ; Yu, Pingchao ; Ge, Hongjuan</creatorcontrib><description>Low-quality data, including insufficient samples and low signal to noise ratio (SNR), restrict the effective application of intelligent diagnostic methods based on deep learning. In this study, a new rolling bearing enhanced diagnostic method is proposed based on swin-transformer (SWT) and ReliefF (RF) combined with Dempster-Shafer (DS) evidence theory. First, SWT is improved for adaptive deep feature mining of the vibration signal. Meanwhile, to enhance the quality of features, RF is introduced to optimize the deep fault features output by the global average pooling layer, which helps improve the classifier performance. Then, the DS evidence theory-based decision fusion strategy is designed to realize the fusion of different axial signals at the decision level, which enhances fault knowledge threshold and further improves the diagnostic ability. Finally, the bearing cases with data collected from the accelerated life degradation and different distributions are studied. The results reveal that the proposed method can adaptively mine fault features with low-quality data and realize efficient enhance diagnosis.</description><identifier>ISSN: 0018-9456</identifier><identifier>EISSN: 1557-9662</identifier><identifier>DOI: 10.1109/TIM.2024.3350130</identifier><identifier>CODEN: IEIMAO</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Adaptation models ; Adaptive feature learning ; Classification tree analysis ; Data models ; Decision theory ; Fault diagnosis ; Feature extraction ; Low SNR ; Multi-sensors ; Roller bearings ; Rolling bearings ; Rotating machinery ; Signal to noise ratio</subject><ispartof>IEEE transactions on instrumentation and measurement, 2024-01, Vol.73, p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-ef48be07c8e4b7845953c55e9b1763015b508678c56182c05b34c2b66cff6d4b3</citedby><cites>FETCH-LOGICAL-c292t-ef48be07c8e4b7845953c55e9b1763015b508678c56182c05b34c2b66cff6d4b3</cites><orcidid>0000-0001-6616-3310 ; 0000-0002-1217-5014 ; 0000-0003-3691-9142 ; 0000-0002-8286-7761 ; 0000-0002-9974-9462 ; 0000-0002-5017-6114 ; 0000-0003-3496-2518</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10381887$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10381887$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chen, Jiayu</creatorcontrib><creatorcontrib>Lin, Cuiying</creatorcontrib><creatorcontrib>Lu, Qinhua</creatorcontrib><creatorcontrib>Yang, Chaoqi</creatorcontrib><creatorcontrib>Li, Peng</creatorcontrib><creatorcontrib>Yu, Pingchao</creatorcontrib><creatorcontrib>Ge, Hongjuan</creatorcontrib><title>A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data</title><title>IEEE transactions on instrumentation and measurement</title><addtitle>TIM</addtitle><description>Low-quality data, including insufficient samples and low signal to noise ratio (SNR), restrict the effective application of intelligent diagnostic methods based on deep learning. In this study, a new rolling bearing enhanced diagnostic method is proposed based on swin-transformer (SWT) and ReliefF (RF) combined with Dempster-Shafer (DS) evidence theory. First, SWT is improved for adaptive deep feature mining of the vibration signal. Meanwhile, to enhance the quality of features, RF is introduced to optimize the deep fault features output by the global average pooling layer, which helps improve the classifier performance. Then, the DS evidence theory-based decision fusion strategy is designed to realize the fusion of different axial signals at the decision level, which enhances fault knowledge threshold and further improves the diagnostic ability. Finally, the bearing cases with data collected from the accelerated life degradation and different distributions are studied. The results reveal that the proposed method can adaptively mine fault features with low-quality data and realize efficient enhance diagnosis.</description><subject>Adaptation models</subject><subject>Adaptive feature learning</subject><subject>Classification tree analysis</subject><subject>Data models</subject><subject>Decision theory</subject><subject>Fault diagnosis</subject><subject>Feature extraction</subject><subject>Low SNR</subject><subject>Multi-sensors</subject><subject>Roller bearings</subject><subject>Rolling bearings</subject><subject>Rotating machinery</subject><subject>Signal to noise ratio</subject><issn>0018-9456</issn><issn>1557-9662</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkDtPwzAYRS0EEqWwMzBYYk75HD8zlj6gUiukUsSEIsdx2lQhbu1EqP-elHZgusu590oHoXsCA0IgeVrNFoMYYjaglAOhcIF6hHMZJULEl6gHQFSUMC6u0U0IWwCQgske-hrisTVlKF2Np-1fvH-uouUUL2yzcTkunMdLV1VlvcbPVvtjTuqNro3N8bjU69qFMuC2zq3Hc_cT7Vtdlc0Bj3Wjb9FVoatg787ZRx_TyWr0Gs3fXmaj4TwycRI3kS2YyixIoyzLpGI84dRwbpOMSEGB8IyDElIZLoiKDfCMMhNnQpiiEDnLaB89nnZ33u1bG5p061pfd5dpdwBxIgXQjoITZbwLwdsi3fnyW_tDSiA9Skw7ielRYnqW2FUeTpXSWvsPp4ooJekvHeZryA</recordid><startdate>20240101</startdate><enddate>20240101</enddate><creator>Chen, Jiayu</creator><creator>Lin, Cuiying</creator><creator>Lu, Qinhua</creator><creator>Yang, Chaoqi</creator><creator>Li, Peng</creator><creator>Yu, Pingchao</creator><creator>Ge, Hongjuan</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-6616-3310</orcidid><orcidid>https://orcid.org/0000-0002-1217-5014</orcidid><orcidid>https://orcid.org/0000-0003-3691-9142</orcidid><orcidid>https://orcid.org/0000-0002-8286-7761</orcidid><orcidid>https://orcid.org/0000-0002-9974-9462</orcidid><orcidid>https://orcid.org/0000-0002-5017-6114</orcidid><orcidid>https://orcid.org/0000-0003-3496-2518</orcidid></search><sort><creationdate>20240101</creationdate><title>A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data</title><author>Chen, Jiayu ; Lin, Cuiying ; Lu, Qinhua ; Yang, Chaoqi ; Li, Peng ; Yu, Pingchao ; Ge, Hongjuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-ef48be07c8e4b7845953c55e9b1763015b508678c56182c05b34c2b66cff6d4b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptation models</topic><topic>Adaptive feature learning</topic><topic>Classification tree analysis</topic><topic>Data models</topic><topic>Decision theory</topic><topic>Fault diagnosis</topic><topic>Feature extraction</topic><topic>Low SNR</topic><topic>Multi-sensors</topic><topic>Roller bearings</topic><topic>Rolling bearings</topic><topic>Rotating machinery</topic><topic>Signal to noise ratio</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Jiayu</creatorcontrib><creatorcontrib>Lin, Cuiying</creatorcontrib><creatorcontrib>Lu, Qinhua</creatorcontrib><creatorcontrib>Yang, Chaoqi</creatorcontrib><creatorcontrib>Li, Peng</creatorcontrib><creatorcontrib>Yu, Pingchao</creatorcontrib><creatorcontrib>Ge, Hongjuan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on instrumentation and measurement</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Jiayu</au><au>Lin, Cuiying</au><au>Lu, Qinhua</au><au>Yang, Chaoqi</au><au>Li, Peng</au><au>Yu, Pingchao</au><au>Ge, Hongjuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data</atitle><jtitle>IEEE transactions on instrumentation and measurement</jtitle><stitle>TIM</stitle><date>2024-01-01</date><risdate>2024</risdate><volume>73</volume><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>0018-9456</issn><eissn>1557-9662</eissn><coden>IEIMAO</coden><abstract>Low-quality data, including insufficient samples and low signal to noise ratio (SNR), restrict the effective application of intelligent diagnostic methods based on deep learning. In this study, a new rolling bearing enhanced diagnostic method is proposed based on swin-transformer (SWT) and ReliefF (RF) combined with Dempster-Shafer (DS) evidence theory. First, SWT is improved for adaptive deep feature mining of the vibration signal. Meanwhile, to enhance the quality of features, RF is introduced to optimize the deep fault features output by the global average pooling layer, which helps improve the classifier performance. Then, the DS evidence theory-based decision fusion strategy is designed to realize the fusion of different axial signals at the decision level, which enhances fault knowledge threshold and further improves the diagnostic ability. Finally, the bearing cases with data collected from the accelerated life degradation and different distributions are studied. The results reveal that the proposed method can adaptively mine fault features with low-quality data and realize efficient enhance diagnosis.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TIM.2024.3350130</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0001-6616-3310</orcidid><orcidid>https://orcid.org/0000-0002-1217-5014</orcidid><orcidid>https://orcid.org/0000-0003-3691-9142</orcidid><orcidid>https://orcid.org/0000-0002-8286-7761</orcidid><orcidid>https://orcid.org/0000-0002-9974-9462</orcidid><orcidid>https://orcid.org/0000-0002-5017-6114</orcidid><orcidid>https://orcid.org/0000-0003-3496-2518</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0018-9456 |
| ispartof | IEEE transactions on instrumentation and measurement, 2024-01, Vol.73, p.1-1 |
| issn | 0018-9456 1557-9662 |
| language | eng |
| recordid | cdi_proquest_journals_2920297603 |
| source | IEEE Electronic Library (IEL) |
| subjects | Adaptation models Adaptive feature learning Classification tree analysis Data models Decision theory Fault diagnosis Feature extraction Low SNR Multi-sensors Roller bearings Rolling bearings Rotating machinery Signal to noise ratio |
| title | A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T07%3A56%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Decision%20Fusion%20SWT-RF%20Method%20for%20Rolling%20Bearing%20Enhanced%20Diagnosis%20under%20Low-quality%20Data&rft.jtitle=IEEE%20transactions%20on%20instrumentation%20and%20measurement&rft.au=Chen,%20Jiayu&rft.date=2024-01-01&rft.volume=73&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=0018-9456&rft.eissn=1557-9662&rft.coden=IEIMAO&rft_id=info:doi/10.1109/TIM.2024.3350130&rft_dat=%3Cproquest_RIE%3E2920297603%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2920297603&rft_id=info:pmid/&rft_ieee_id=10381887&rfr_iscdi=true |