EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transformer Fault Diagnosis Based on Knowledge Distillation and Residual Convolutional Neural Networks

Haikun Shang iD, Yanlei Wei iD, Shen Zhang

Entropy · 23.06.2025 · 27 (7) · 669

DOI: 10.3390/e27070669 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 23.06.2025. Verfasst von Haikun Shang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education, Northeast Electric Power Universit…. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Natural Science Foundation of Jilin Province, China, Natural Science Foundation of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dissolved Gas Analysis (DGA) of transformer oil is a critical technique for transformer fault diagnosis that involves analyzing the concentration of gases to detect potential transformer faults in a timely manner. Given the issues of large model parameters and high computational resource demands in transformer DGA diagnostics, this study proposes a lightweight convolutional neural network (CNN) model for improving gas ratio methods, combining Knowledge Distillation (KD) and recursive plots. The approach begins by extracting features from DGA data using the ratio method and Multiscale sample entropy (MSE), then reconstructs the state space of the feature data using recursive plots to generate interpretable two-dimensional image features. A deep feature extraction process is performed using the ResNet50 model, integrated with the Convolutional Block Attention Module (CBAM). Subsequently, the Sparrow Optimization Algorithm (SSA) is applied to optimize the hyperparameters of the ResNet50 model, which is trained on DGA data as the teacher model. Finally, a dual-path distillation mechanism is introduced to transfer the efficient features and knowledge from the teacher model to the student model, MobileNetV3-Large. The experimental results show that the distilled model reduces memory usage by 83.5% and computation time by 73.2%, significantly lowering computational complexity while achieving favorable performance across various evaluation metrics. This provides a novel technical solution for the improvement of gas ratio methods.

Schlagwörter

Stichwörter der Autor:innen

CBAMCNNsDGAknowledge distillationrecursive plotssample entropytransformer

Autor:innen und Institutionen

  • Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education, Northeast Electric Power University, Jilin 132012, China.

ORCID-Profile: Haikun Shang, Yanlei Wei

Förderung

  • the Natural Science Foundation of Jilin Province, China
  • Natural Science Foundation of Jilin Province

Zitieren

APA

Shang, H., Wei, Y., & Zhang, S. (2025). Transformer Fault Diagnosis Based on Knowledge Distillation and Residual Convolutional Neural Networks. Entropy, 27(7), 669. https://doi.org/10.3390/e27070669

Vancouver

Shang H, Wei Y, Zhang S. Transformer Fault Diagnosis Based on Knowledge Distillation and Residual Convolutional Neural Networks. Entropy. 2025;27(7):669. doi:10.3390/e27070669

BibTeX
@article{Shang2025,
  author = {Shang, Haikun and Wei, Yanlei and Zhang, Shen},
  title = {Transformer Fault Diagnosis Based on Knowledge Distillation and Residual Convolutional Neural Networks},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {7},
  pages = {669},
  doi = {10.3390/e27070669}
}
Kostenlos starten →