EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Classification of Transformer Inrush and Fault Currents Using a Hybrid Self-Organizing Map and CNN Model

Heungseok Lee, Sang-Hee Kang, Soon-Ryul Nam

Energies · 11.10.2025 · 18 (20) · 5351

DOI: 10.3390/en18205351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 11.10.2025. Verfasst von Heungseok Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Electric Power Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate classification between magnetizing inrush currents and internal faults is essential for reliable transformer protection and stable power system operation. Because their transient waveforms are so similar, conventional differential protection and harmonic restraint techniques often fail under dynamic conditions. This study presents a two-stage classification model that combines a self-organizing map (SOM) and a convolutional neural network (CNN) to enhance robustness and accuracy in distinguishing between inrush currents and internal faults in power transformers. In the first stage, an unsupervised SOM identifies topologically structured event clusters without the need for labeled data or predefined thresholds. Seven features are extracted from differential current signals to form fixed-length input vectors. These vectors are projected onto a two-dimensional SOM grid to capture inrush and fault distributions. In the second stage, the SOM’s activation maps are converted to grayscale images and classified by a CNN, thereby merging the interpretability of clustering with the performance of deep learning. Simulation data from a 154 kV MATLAB/Simulink transformer model includes inrush, internal fault, and overlapping events. Results show that after one cycle following fault inception, the proposed method improves accuracy (AC), precision (PR), recall (RC), and F1-score (F1s) by up to 3% compared with a conventional CNN model, demonstrating its suitability for real-time transformer protection.

Förderung

  • Korea Electric Power Corporation

Zitieren

APA

Lee, H., Kang, S., & Nam, S. (2025). Deep Learning-Based Classification of Transformer Inrush and Fault Currents Using a Hybrid Self-Organizing Map and CNN Model. Energies, 18(20), 5351. https://doi.org/10.3390/en18205351

Vancouver

Lee H, Kang S, Nam S. Deep Learning-Based Classification of Transformer Inrush and Fault Currents Using a Hybrid Self-Organizing Map and CNN Model. Energies. 2025;18(20):5351. doi:10.3390/en18205351

BibTeX
@article{Lee2025,
  author = {Lee, Heungseok and Kang, Sang-Hee and Nam, Soon-Ryul},
  title = {Deep Learning-Based Classification of Transformer Inrush and Fault Currents Using a Hybrid Self-Organizing Map and CNN Model},
  journal = {Energies},
  year = {2025},
  volume = {18},
  number = {20},
  pages = {5351},
  doi = {10.3390/en18205351}
}
Kostenlos starten →