A Hybrid Machine Learning Framework for Early Fault Detection in Power Transformers Using PSO and DMO Algorithms DOI Creative Commons

Mohammed Alenezi,

Fatih Anayi, Michael Packianather

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(8), P. 2024 - 2024

Published: April 15, 2025

The early detection of faults in power transformers is crucial for ensuring operational reliability and minimizing system disruptions. This study introduces a novel machine learning framework that integrates Particle Swarm Optimization (PSO) Dwarf Mongoose (DMO) algorithms feature selection hyperparameter tuning, combined with advanced classifiers such as Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM). A 5-fold cross-validation approach was employed to ensure robust performance evaluation. Feature extraction performed using both Discrete Wavelet Decomposition (DWD) Matching Pursuit (MP), providing comprehensive representation the dataset comprising 2400 samples 41 extracted features. Experimental validation demonstrated efficacy proposed framework. PSO-optimized RF model achieved highest accuracy 97.71%, precision 98.02% an F1 score 98.63%, followed by PSO-DT 95.00% accuracy. Similarly, DMO-optimized recorded 98.33%, 98.80% 99.04%, outperforming other DMO-based classifiers. demonstrates significant advancements transformer protection enabling accurate fault detection, thereby enhancing safety systems.

Language: Английский

A Comprehensive Review of Transformer Winding Diagnostics: Integrating Frequency Response Analysis with Machine Learning Approaches DOI Creative Commons

Meysam Beheshti Asl,

I. Fofana, F. Meghnefi

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(5), P. 1209 - 1209

Published: March 1, 2025

Frequency Response Analysis (FRA) is a proven method for detecting mechanical faults in transformers, such as winding deformations and short circuits. However, traditional FRA interpretation relies heavily on visual subjective comparison of frequency response curves, which can introduce human bias lead to inconsistent results. Integrating Machine Learning (ML) with significantly enhance fault diagnosis by automatically identifying complex patterns within the data that are difficult detect using through analysis. This integration automate diagnostics, accuracy, improve predictive maintenance, reduce reliance expert curtail operational costs. paper reviews application ML alongside complementary techniques transformer health assessment.

Language: Английский

Citations

2
Enhancing fault detection and classification in distribution transformers using non-contact magnetic measurements: A comparative study of tree models and neural networks DOI

S.N.Tirumala Rao,

Syed Ali Abbas Kazmi, Muhammad Iftikhar

et al.

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 3469 - 3488

Published: March 18, 2025

Language: Английский

Citations

0
A Hybrid Machine Learning Framework for Early Fault Detection in Power Transformers Using PSO and DMO Algorithms DOI Creative Commons

Mohammed Alenezi,

Fatih Anayi, Michael Packianather

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(8), P. 2024 - 2024

Published: April 15, 2025

The early detection of faults in power transformers is crucial for ensuring operational reliability and minimizing system disruptions. This study introduces a novel machine learning framework that integrates Particle Swarm Optimization (PSO) Dwarf Mongoose (DMO) algorithms feature selection hyperparameter tuning, combined with advanced classifiers such as Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM). A 5-fold cross-validation approach was employed to ensure robust performance evaluation. Feature extraction performed using both Discrete Wavelet Decomposition (DWD) Matching Pursuit (MP), providing comprehensive representation the dataset comprising 2400 samples 41 extracted features. Experimental validation demonstrated efficacy proposed framework. PSO-optimized RF model achieved highest accuracy 97.71%, precision 98.02% an F1 score 98.63%, followed by PSO-DT 95.00% accuracy. Similarly, DMO-optimized recorded 98.33%, 98.80% 99.04%, outperforming other DMO-based classifiers. demonstrates significant advancements transformer protection enabling accurate fault detection, thereby enhancing safety systems.

Language: Английский

Citations

0