PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 14, 2026IET Communications0 citationsOpen Access

Multi‐Perspective Transmission Line Fault Causation Identification Via Wavelet Attention Boosting

View Full Paper
YZYue ZhangZLZhiqiang LinKWKunfeng Wei

Key Points

  • This research aims to improve the accuracy of identifying the causes of transmission line faults by incorporating multi-perspective data.
  • Developed a multi-perspective fault identification framework using wavelet attention and adaptive correlation fusion.
  • Constructed an energy matrix with a multi-scale continuous wavelet transform to enhance signal features.
  • Implemented a cross-attention mechanism to integrate dynamic and static features effectively.
  • Achieved an accuracy of 94.29% and a recall of 93.10%, surpassing the second-best method by 0.86 and 3.1 percentage points, respectively.
  • Numerous evaluation metrics significantly outperformed existing baseline methods.

Abstract

ABSTRACT Accurate identification of transmission line fault causes is crucial for enhancing grid reliability and improving fault handling efficiency. Although deep learning techniques have advanced fault cause identification, existing methods still exhibit deficiencies in capturing global contextual information, suppressing noise interference and effectively integrating multi‐perspective information such as weather and temporal data. To address these limitations, this paper proposes a multi‐perspective fault identification framework integrating wavelet attention enhancement and adaptive correlation fusion. The method initially constructs an energy matrix through a multi‐scale continuous wavelet transform, utilizing prior knowledge of fault‐related frequency components to guide attention weight allocation, thereby enhancing critical signal features while suppressing noise. Subsequently, a learnable weight matrix is introduced to explicitly model the differential contributions of the static features—including weather, date and time—to the fused features, enabling adaptive multi‐perspective fusion. Furthermore, a cross‐attention mechanism is designed to capture deep interactions between dynamic fault recording features and the static contextual features, achieving cross‐perspective deep integration. Experimental results on a real‐world fault dataset demonstrate the superior performance of the proposed method, attaining an accuracy of 94.29% and a recall of 93.10%. These values exceed those of the second‐best configuration by approximately 0.86 and 3.1 percentage points, respectively. Multiple other evaluation metrics also significantly outperform existing baseline methods.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a0566fba550a87e60a1efe7https://doi.org/10.1049/cmu2.70166
Ask AI
Helpful
Bookmark
Share
View Full Paper