Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning

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) tec...

Full description

Saved in:
Bibliographic Details
Main Authors: Awad Almehdhar, Radek Prochazka
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850127489562574848
author Awad Almehdhar
Radek Prochazka
author_facet Awad Almehdhar
Radek Prochazka
author_sort Awad Almehdhar
collection DOAJ
description 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.
format Article
id doaj-art-d305d316872d4b278ff231e82ceb8a5e
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d305d316872d4b278ff231e82ceb8a5e2025-08-20T02:33:39ZengMDPI AGApplied Sciences2076-34172025-05-011510545510.3390/app15105455Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep LearningAwad Almehdhar0Radek Prochazka1Faculty of Electrical Engineering, Czech Technical University in Prague, Technická 2, 166 27 Prague, Czech RepublicFaculty of Electrical Engineering, Czech Technical University in Prague, Technická 2, 166 27 Prague, Czech RepublicPartial 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.https://www.mdpi.com/2076-3417/15/10/5455partial dischargefinite element methodtime–frequency analysisdeep learningconvolutional neural networkhigh-voltage insulation
spellingShingle Awad Almehdhar
Radek Prochazka
Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
Applied Sciences
partial discharge
finite element method
time–frequency analysis
deep learning
convolutional neural network
high-voltage insulation
title Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
title_full Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
title_fullStr Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
title_full_unstemmed Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
title_short Classification of Multiple Partial Discharge Sources Using Time-Frequency Analysis and Deep Learning
title_sort classification of multiple partial discharge sources using time frequency analysis and deep learning
topic partial discharge
finite element method
time–frequency analysis
deep learning
convolutional neural network
high-voltage insulation
url https://www.mdpi.com/2076-3417/15/10/5455
work_keys_str_mv AT awadalmehdhar classificationofmultiplepartialdischargesourcesusingtimefrequencyanalysisanddeeplearning
AT radekprochazka classificationofmultiplepartialdischargesourcesusingtimefrequencyanalysisanddeeplearning