Academic Journal
Προβολή σε EDS

CAG-Net: A Novel Change Attention Guided Network for Substation Defect Detection.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: CAG-Net: A Novel Change Attention Guided Network for Substation Defect Detection.
Συγγραφείς: Xiang, Dao1 (AUTHOR), Du, Xiaofei2 (AUTHOR), Liu, Zhaoyang1 (AUTHOR) zy.liu@cumt.edu.cn
Πηγή: Mathematics (2227-7390). Jan2026, Vol. 14 Issue 1, p178. 19p.
Θεματικοί όροι: *Detection algorithms, *Defect tracking (Computer software development), *Artificial neural networks
Περίληψη: Timely detection and handling of substation defects plays a foundational role in ensuring the stable operation of power systems. Existing substation defect detection methods fail to make full use of the temporal information contained in substation inspection samples, resulting in problems such as weak generalization ability and susceptibility to background interference. To address these issues, a change attention guided substation defect detection algorithm (CAG-Net) based on a dual-temporal encoder–decoder framework is proposed. The encoder module employs a Siamese backbone network composed of efficient local-global context aggregation modules to extract multi-scale features, balancing local details and global semantics, and designs a change attention guidance module that takes feature differences as attention weights to dynamically enhance the saliency of defect regions and suppress background interference. The decoder module adopts an improved FPN structure to fuse high-level and low-level features, supplement defect details, and improve the model's ability to detect small targets and multi-scale defects. Experimental results on the self-built substation multi-phase defect dataset (SMDD) show that the proposed method achieves 81.76% in terms of mAP, which is 3.79% higher than that of Faster R-CNN and outperforms mainstream detection models such as GoldYOLO and YOLOv10. Ablation experiments and visualization analysis demonstrate that the method can effectively focus on defect regions in complex environments, improving the positioning accuracy of multi-scale targets. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Academic Search Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=22277390&ISBN=&volume=14&issue=1&date=20260101&spage=178&pages=178-196&title=Mathematics (2227-7390)&atitle=CAG-Net%3A%20A%20Novel%20Change%20Attention%20Guided%20Network%20for%20Substation%20Defect%20Detection.&aulast=Xiang%2C%20Dao&id=DOI:10.3390/math14010178
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: asx
DbLabel: Academic Search Index
An: 190823347
RelevancyScore: 1411
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1411.06604003906
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CAG-Net: A Novel Change Attention Guided Network for Substation Defect Detection.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xiang%2C+Dao%22">Xiang, Dao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Du%2C+Xiaofei%22">Du, Xiaofei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Zhaoyang%22">Liu, Zhaoyang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zy.liu@cumt.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Mathematics+%282227-7390%29%22">Mathematics (2227-7390)</searchLink>. Jan2026, Vol. 14 Issue 1, p178. 19p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Detection+algorithms%22">Detection algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Defect+tracking+%28Computer+software+development%29%22">Defect tracking (Computer software development)</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Timely detection and handling of substation defects plays a foundational role in ensuring the stable operation of power systems. Existing substation defect detection methods fail to make full use of the temporal information contained in substation inspection samples, resulting in problems such as weak generalization ability and susceptibility to background interference. To address these issues, a change attention guided substation defect detection algorithm (CAG-Net) based on a dual-temporal encoder–decoder framework is proposed. The encoder module employs a Siamese backbone network composed of efficient local-global context aggregation modules to extract multi-scale features, balancing local details and global semantics, and designs a change attention guidance module that takes feature differences as attention weights to dynamically enhance the saliency of defect regions and suppress background interference. The decoder module adopts an improved FPN structure to fuse high-level and low-level features, supplement defect details, and improve the model's ability to detect small targets and multi-scale defects. Experimental results on the self-built substation multi-phase defect dataset (SMDD) show that the proposed method achieves 81.76% in terms of mAP, which is 3.79% higher than that of Faster R-CNN and outperforms mainstream detection models such as GoldYOLO and YOLOv10. Ablation experiments and visualization analysis demonstrate that the method can effectively focus on defect regions in complex environments, improving the positioning accuracy of multi-scale targets. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=190823347
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/math14010178
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 178
    Subjects:
      – SubjectFull: Detection algorithms
        Type: general
      – SubjectFull: Defect tracking (Computer software development)
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: CAG-Net: A Novel Change Attention Guided Network for Substation Defect Detection.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xiang, Dao
      – PersonEntity:
          Name:
            NameFull: Du, Xiaofei
      – PersonEntity:
          Name:
            NameFull: Liu, Zhaoyang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: Jan2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 22277390
          Numbering:
            – Type: volume
              Value: 14
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Mathematics (2227-7390)
              Type: main
ResultId 1