View in EDS HTML Full Text PDF Full Text

A temporal-frequency contrastive learing method for acoustic-based mechanical fault detection in gas-insulated switch-gear.

Saved in:
Bibliographic Details
Title: A temporal-frequency contrastive learing method for acoustic-based mechanical fault detection in gas-insulated switch-gear.
Authors: Sheng, Yeduo1 (AUTHOR), Zhang, Bo2 (AUTHOR), Zhang, Zipeng1 (AUTHOR), Shao, Yuying3 (AUTHOR), Yuan, Guogang4 (AUTHOR), Liu, Jianshu1 (AUTHOR), Liu, Houguang1 (AUTHOR) liuhg@cumt.edu.cn
Source: Nondestructive Testing & Evaluation. Aug2026, Vol. 41 Issue 8, p4541-4563. 23p.
Subjects: Time-frequency analysis, Contrastive learning, Fault diagnosis, Machine learning
Abstract: Although data-driven acoustic-based fault diagnosis has achieved satisfactory results for gas-insulated switchgear (GIS) under the massive labelled datasets built in laboratory conditions, it remains challenging to ensure accurate and robust diagnosis when facing limited fault samples and operational variability in real-world scenarios. To address this, this paper proposes a novel time-frequency self-supervised contrastive learning method for GIS fault diagnosis under small-sample and diverse operational conditions. The method adopts a pre-train and fine-tune framework to extract shared discriminative features across different domains. In the pre-train stage, an unsupervised contrastive learning strategy is used to learn the physical consistency of information in the time-frequency domain of mechanical faults. In the fine-tune stage, only 5% of the labelled target data is required to adapt the model using the shared representations from pre-training. Experiments on laboratory and field data validate the effectiveness of the proposed method, which achieves 97.64% accuracy and shows competitive generalisation and robustness compared to existing methods. [ABSTRACT FROM AUTHOR]
Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 195547628
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A temporal-frequency contrastive learing method for acoustic-based mechanical fault detection in gas-insulated switch-gear.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sheng%2C+Yeduo%22">Sheng, Yeduo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Bo%22">Zhang, Bo</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zipeng%22">Zhang, Zipeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shao%2C+Yuying%22">Shao, Yuying</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yuan%2C+Guogang%22">Yuan, Guogang</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Jianshu%22">Liu, Jianshu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Houguang%22">Liu, Houguang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> liuhg@cumt.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Nondestructive+Testing+%26+Evaluation%22">Nondestructive Testing & Evaluation</searchLink>. Aug2026, Vol. 41 Issue 8, p4541-4563. 23p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Time-frequency+analysis%22">Time-frequency analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Contrastive+learning%22">Contrastive learning</searchLink><br /><searchLink fieldCode="DE" term="%22Fault+diagnosis%22">Fault diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Although data-driven acoustic-based fault diagnosis has achieved satisfactory results for gas-insulated switchgear (GIS) under the massive labelled datasets built in laboratory conditions, it remains challenging to ensure accurate and robust diagnosis when facing limited fault samples and operational variability in real-world scenarios. To address this, this paper proposes a novel time-frequency self-supervised contrastive learning method for GIS fault diagnosis under small-sample and diverse operational conditions. The method adopts a pre-train and fine-tune framework to extract shared discriminative features across different domains. In the pre-train stage, an unsupervised contrastive learning strategy is used to learn the physical consistency of information in the time-frequency domain of mechanical faults. In the fine-tune stage, only 5% of the labelled target data is required to adapt the model using the shared representations from pre-training. Experiments on laboratory and field data validate the effectiveness of the proposed method, which achieves 97.64% accuracy and shows competitive generalisation and robustness compared to existing methods. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Nondestructive Testing & Evaluation is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=195547628
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/10589759.2025.2541050
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 4541
    Subjects:
      – SubjectFull: Time-frequency analysis
        Type: general
      – SubjectFull: Contrastive learning
        Type: general
      – SubjectFull: Fault diagnosis
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: A temporal-frequency contrastive learing method for acoustic-based mechanical fault detection in gas-insulated switch-gear.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sheng, Yeduo
      – PersonEntity:
          Name:
            NameFull: Zhang, Bo
      – PersonEntity:
          Name:
            NameFull: Zhang, Zipeng
      – PersonEntity:
          Name:
            NameFull: Shao, Yuying
      – PersonEntity:
          Name:
            NameFull: Yuan, Guogang
      – PersonEntity:
          Name:
            NameFull: Liu, Jianshu
      – PersonEntity:
          Name:
            NameFull: Liu, Houguang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 10589759
          Numbering:
            – Type: volume
              Value: 41
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Nondestructive Testing & Evaluation
              Type: main
ResultId 1