Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description

Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on industrial electronics (1982) 2023-08, Vol.70 (8), p.8488-8498
Hauptverfasser: Ni, Xueqing, Yang, Dongsheng, Zhang, Huaguang, Qu, Fuming, Qin, Jia
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 8498
container_issue 8
container_start_page 8488
container_title IEEE transactions on industrial electronics (1982)
container_volume 70
creator Ni, Xueqing
Yang, Dongsheng
Zhang, Huaguang
Qu, Fuming
Qin, Jia
description Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer learning (TSTL) method is proposed, which contains two phases: first, early stage series are transferred to their corresponding serious stage for fault feature enhancement. Moreover, due to the improvement of model structure and loss function, the limitation of mismatched working condition is well-weaken. Second, a transferred fault mode recognition model is trained by using transferred normal series that provides a novel solution for data imbalance. Finally, the TSTL method is verified by actual vibration datasets of power pole tower bolts. Its superiority in feature transfer and fault detection is confirmed by several groups of comparative experiments and results demonstrate TSTL outperforms mainstream methods.
doi_str_mv 10.1109/TIE.2022.3229351
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9994777</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9994777</ieee_id><sourcerecordid>2787704722</sourcerecordid><originalsourceid>FETCH-LOGICAL-c254t-27e8cf13ee03534ccdaf151b3b9b00fddb8b16282221d4cfacb2ea1c984b12f3</originalsourceid><addsrcrecordid>eNo9kUFLwzAUgIMoOKd3wUvAc2eStkvrbbpNBxMPK17La_q6dbRpTVJh_8Sfa8aGpxD43pfwPULuOZtwztKnbLWYCCbEJBQiDWN-QUY8jmWQplFySUZMyCRgLJpekxtr94zxKObxiPxmdYvBBk2NlmYGtK3Q0DWC0bXePtOZpgswzYFuHGyRrtoCGtAK6RKGxtE5OlSu7jT9QLfrSvoCFkvq70sENxikC7078i1qR0GX3tCb7sczm6HvO-Polxd0hs7BgddZZer-KLwlVxU0Fu_O55hky0X2-h6sP99Wr7N1oEQcuUBITFTFQ0QWxmGkVAkVj3kRFmnBWFWWRVLwqUiEELyMVAWqEAhcpUlUcFGFY_J40vpffQ9oXb7vBqP9i7kvJiWLpBCeYidKmc5ag1Xem7oFc8g5y4_5c58_P-bPz_n9yMNppEbEfzz165BShn-fFYMA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2787704722</pqid></control><display><type>article</type><title>Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description</title><source>IEEE Electronic Library (IEL)</source><creator>Ni, Xueqing ; Yang, Dongsheng ; Zhang, Huaguang ; Qu, Fuming ; Qin, Jia</creator><creatorcontrib>Ni, Xueqing ; Yang, Dongsheng ; Zhang, Huaguang ; Qu, Fuming ; Qin, Jia</creatorcontrib><description>Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer learning (TSTL) method is proposed, which contains two phases: first, early stage series are transferred to their corresponding serious stage for fault feature enhancement. Moreover, due to the improvement of model structure and loss function, the limitation of mismatched working condition is well-weaken. Second, a transferred fault mode recognition model is trained by using transferred normal series that provides a novel solution for data imbalance. Finally, the TSTL method is verified by actual vibration datasets of power pole tower bolts. Its superiority in feature transfer and fault detection is confirmed by several groups of comparative experiments and results demonstrate TSTL outperforms mainstream methods.</description><identifier>ISSN: 0278-0046</identifier><identifier>EISSN: 1557-9948</identifier><identifier>DOI: 10.1109/TIE.2022.3229351</identifier><identifier>CODEN: ITIED6</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Data imbalance ; Data models ; early stage fault detection ; Employee welfare ; Fault detection ; feature enhancement ; Feature extraction ; Generative adversarial networks ; Generators ; Learning ; mismatched working condition ; power pole tower ; Task analysis ; Time series</subject><ispartof>IEEE transactions on industrial electronics (1982), 2023-08, Vol.70 (8), p.8488-8498</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c254t-27e8cf13ee03534ccdaf151b3b9b00fddb8b16282221d4cfacb2ea1c984b12f3</citedby><cites>FETCH-LOGICAL-c254t-27e8cf13ee03534ccdaf151b3b9b00fddb8b16282221d4cfacb2ea1c984b12f3</cites><orcidid>0000-0003-1262-5975 ; 0000-0002-2375-9824 ; 0000-0002-8072-9568 ; 0000-0002-4102-5672</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9994777$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9994777$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ni, Xueqing</creatorcontrib><creatorcontrib>Yang, Dongsheng</creatorcontrib><creatorcontrib>Zhang, Huaguang</creatorcontrib><creatorcontrib>Qu, Fuming</creatorcontrib><creatorcontrib>Qin, Jia</creatorcontrib><title>Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description</title><title>IEEE transactions on industrial electronics (1982)</title><addtitle>TIE</addtitle><description>Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer learning (TSTL) method is proposed, which contains two phases: first, early stage series are transferred to their corresponding serious stage for fault feature enhancement. Moreover, due to the improvement of model structure and loss function, the limitation of mismatched working condition is well-weaken. Second, a transferred fault mode recognition model is trained by using transferred normal series that provides a novel solution for data imbalance. Finally, the TSTL method is verified by actual vibration datasets of power pole tower bolts. Its superiority in feature transfer and fault detection is confirmed by several groups of comparative experiments and results demonstrate TSTL outperforms mainstream methods.</description><subject>Data imbalance</subject><subject>Data models</subject><subject>early stage fault detection</subject><subject>Employee welfare</subject><subject>Fault detection</subject><subject>feature enhancement</subject><subject>Feature extraction</subject><subject>Generative adversarial networks</subject><subject>Generators</subject><subject>Learning</subject><subject>mismatched working condition</subject><subject>power pole tower</subject><subject>Task analysis</subject><subject>Time series</subject><issn>0278-0046</issn><issn>1557-9948</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kUFLwzAUgIMoOKd3wUvAc2eStkvrbbpNBxMPK17La_q6dbRpTVJh_8Sfa8aGpxD43pfwPULuOZtwztKnbLWYCCbEJBQiDWN-QUY8jmWQplFySUZMyCRgLJpekxtr94zxKObxiPxmdYvBBk2NlmYGtK3Q0DWC0bXePtOZpgswzYFuHGyRrtoCGtAK6RKGxtE5OlSu7jT9QLfrSvoCFkvq70sENxikC7078i1qR0GX3tCb7sczm6HvO-Polxd0hs7BgddZZer-KLwlVxU0Fu_O55hky0X2-h6sP99Wr7N1oEQcuUBITFTFQ0QWxmGkVAkVj3kRFmnBWFWWRVLwqUiEELyMVAWqEAhcpUlUcFGFY_J40vpffQ9oXb7vBqP9i7kvJiWLpBCeYidKmc5ag1Xem7oFc8g5y4_5c58_P-bPz_n9yMNppEbEfzz165BShn-fFYMA</recordid><startdate>20230801</startdate><enddate>20230801</enddate><creator>Ni, Xueqing</creator><creator>Yang, Dongsheng</creator><creator>Zhang, Huaguang</creator><creator>Qu, Fuming</creator><creator>Qin, Jia</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>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-1262-5975</orcidid><orcidid>https://orcid.org/0000-0002-2375-9824</orcidid><orcidid>https://orcid.org/0000-0002-8072-9568</orcidid><orcidid>https://orcid.org/0000-0002-4102-5672</orcidid></search><sort><creationdate>20230801</creationdate><title>Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description</title><author>Ni, Xueqing ; Yang, Dongsheng ; Zhang, Huaguang ; Qu, Fuming ; Qin, Jia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c254t-27e8cf13ee03534ccdaf151b3b9b00fddb8b16282221d4cfacb2ea1c984b12f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Data imbalance</topic><topic>Data models</topic><topic>early stage fault detection</topic><topic>Employee welfare</topic><topic>Fault detection</topic><topic>feature enhancement</topic><topic>Feature extraction</topic><topic>Generative adversarial networks</topic><topic>Generators</topic><topic>Learning</topic><topic>mismatched working condition</topic><topic>power pole tower</topic><topic>Task analysis</topic><topic>Time series</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ni, Xueqing</creatorcontrib><creatorcontrib>Yang, Dongsheng</creatorcontrib><creatorcontrib>Zhang, Huaguang</creatorcontrib><creatorcontrib>Qu, Fuming</creatorcontrib><creatorcontrib>Qin, Jia</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 &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on industrial electronics (1982)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ni, Xueqing</au><au>Yang, Dongsheng</au><au>Zhang, Huaguang</au><au>Qu, Fuming</au><au>Qin, Jia</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description</atitle><jtitle>IEEE transactions on industrial electronics (1982)</jtitle><stitle>TIE</stitle><date>2023-08-01</date><risdate>2023</risdate><volume>70</volume><issue>8</issue><spage>8488</spage><epage>8498</epage><pages>8488-8498</pages><issn>0278-0046</issn><eissn>1557-9948</eissn><coden>ITIED6</coden><abstract>Early stage fault detection plays a pivotal role in Industrial equipment accidents avoidance and scientific maintenance. While limited by the complex operation background, its application encounters with the conundrum of fault feature indistinctness. To address the challenge, a time-series transfer learning (TSTL) method is proposed, which contains two phases: first, early stage series are transferred to their corresponding serious stage for fault feature enhancement. Moreover, due to the improvement of model structure and loss function, the limitation of mismatched working condition is well-weaken. Second, a transferred fault mode recognition model is trained by using transferred normal series that provides a novel solution for data imbalance. Finally, the TSTL method is verified by actual vibration datasets of power pole tower bolts. Its superiority in feature transfer and fault detection is confirmed by several groups of comparative experiments and results demonstrate TSTL outperforms mainstream methods.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TIE.2022.3229351</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0003-1262-5975</orcidid><orcidid>https://orcid.org/0000-0002-2375-9824</orcidid><orcidid>https://orcid.org/0000-0002-8072-9568</orcidid><orcidid>https://orcid.org/0000-0002-4102-5672</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 0278-0046
ispartof IEEE transactions on industrial electronics (1982), 2023-08, Vol.70 (8), p.8488-8498
issn 0278-0046
1557-9948
language eng
recordid cdi_ieee_primary_9994777
source IEEE Electronic Library (IEL)
subjects Data imbalance
Data models
early stage fault detection
Employee welfare
Fault detection
feature enhancement
Feature extraction
Generative adversarial networks
Generators
Learning
mismatched working condition
power pole tower
Task analysis
Time series
title Time-Series Transfer Learning: An Early Stage Imbalance Fault Detection Method Based on Feature Enhancement and Improved Support Vector Data Description
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T16%3A31%3A34IST&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=Time-Series%20Transfer%20Learning:%20An%20Early%20Stage%20Imbalance%20Fault%20Detection%20Method%20Based%20on%20Feature%20Enhancement%20and%20Improved%20Support%20Vector%20Data%20Description&rft.jtitle=IEEE%20transactions%20on%20industrial%20electronics%20(1982)&rft.au=Ni,%20Xueqing&rft.date=2023-08-01&rft.volume=70&rft.issue=8&rft.spage=8488&rft.epage=8498&rft.pages=8488-8498&rft.issn=0278-0046&rft.eissn=1557-9948&rft.coden=ITIED6&rft_id=info:doi/10.1109/TIE.2022.3229351&rft_dat=%3Cproquest_RIE%3E2787704722%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=2787704722&rft_id=info:pmid/&rft_ieee_id=9994777&rfr_iscdi=true