Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
Applied Sciences · 13.05.2025 · 15 (10) · 5455
DOI: 10.3390/app15105455 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 13.05.2025. Verfasst von Awad Almehdhar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Czech Office for Standards, Metrology and Testing, under the Metrology Development Program 2025, Czech Technical University in Prague.
Abstract (Originalsprache)
Partial discharge (PD) analysis is critical for diagnosing insulation degradation in high-voltage equipment. While conventional methods struggle with multi-source PD classification due to signal overlap and noise, this study proposes a hybrid approach combining five time–frequency analysis (TFA) techniques with deep learning (GoogLeNet for simulation, ResNet50 for experiments). PD data are generated through Finite Element Method (FEM) simulations and validated via laboratory experiments. The Scatter Wavelet Transform (SWT) achieves 96.67% accuracy (F1-score: 0.967) in simulation and perfect 100% accuracy (F1-score: 1.000) in experiments, outperforming other TFAs like HHT (70.00% experimental accuracy). The Wigner–Ville Distribution (WVD) also shows strong experimental performance (94.74% accuracy, AUC: 0.947), though its computational complexity limits real-time use. These results demonstrate the SWT’s superiority in handling real-world noise and multi-source PD signals, providing a robust framework for insulation diagnostics in power systems.
Förderung
- Czech Office for Standards, Metrology and Testing, under the Metrology Development Program 2025
- Czech Technical University in Prague
Zitieren
APA
Almehdhar, A., & Prochazka, R. (2025). Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning. Applied Sciences, 15(10), 5455. https://doi.org/10.3390/app15105455
Vancouver
Almehdhar A, Prochazka R. Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning. Applied Sciences. 2025;15(10):5455. doi:10.3390/app15105455
BibTeX
@article{Almehdhar2025,
author = {Almehdhar, Awad and Prochazka, Radek},
title = {Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {10},
pages = {5455},
doi = {10.3390/app15105455}
}
EUVIMED