FAULT DIAGNOSIS IN POWER TRANSFORMERS USING RESAMPLED DISSOLVED GAS ANALYSIS AND MACHINE LEARNING
DOI:
https://doi.org/10.59277/RRST-EE.2026.2.13Keywords:
Power Transformer, Hybrid sampling, Support vector machine (SMVM), Dissolved gas analysis (DGA), Imbalanced datasetAbstract
Fault diagnosis in power transformers is essential for ensuring operational reliability and minimizing maintenance downtime. This paper presents a hybrid machine learning framework that leverages advanced resampling and optimization techniques to enhance fault classification accuracy using dissolved gas analysis (DGA). To address class imbalance in the dataset, resampling methods such as SMOTE-ENN and ADASYN are employed. Three classifiers, namely nonlinear support vector machine (NLSVM), linear discriminant analysis (LDA), and artificial neural networks (ANN) are evaluated, with hyperparameter tuning performed using gradient-based optimizer function (GFO) and firefly optimization (FFO). Among them, the FFO-optimized NLSVM combined with SMOTE-ENN achieved the highest performance, with a recognition rate of 98.7%. The results, validated through confusion matrices and ROC analysis, demonstrate the robustness of the proposed approach. This framework provides an effective and reliable tool for condition-based maintenance, enabling precise multi-class fault identification in power transformers.
References
(1) A. Christina, M.A. Salam, Q.M. Rahman, F. Wen, S.P. Ang, W. Voon, Causes of transformer failures and diagnostic methods – A review, Renew. Sustain. Energy Rev., 82, pp. 1442–1456 (2017).
(2) A. Moeini, M. Dabbaghjamanesh, T. Dragičević, J.W. Kimball, J. Zhang, Machine learning technique for low-frequency modulation techniques in power converters, Control of Power Electronic Converters and Systems, Academic Press, pp. 149–167 (2021).
(3) Y. Wang, X. Zeng, Z. Dong, Y. Huang, Novel protection scheme of stator single-phase-to-ground fault for power formers, Int. J. Electr. Power Energy Syst., 53, pp. 321–328 (2013).
(4) J. Zhao, Y. Xu, F. Luo, Z. Dong, Y. Peng, Power system fault diagnosis based on history-driven differential evolution and stochastic time domain simulation, Inf. Sci., 275, pp. 13–29 (2014).
(5) L. Wang, X. Zhao, J. Pei, G. Tang, Transformer fault diagnosis using continuous sparse autoencoder, SpringerPlus, 5, 1, pp. 1–10 (2016).
(6) J. Dai, H. Song, G. Sheng, X. Jiang, Dissolved gas analysis of insulating oil for power transformer fault diagnosis with deep belief network, IEEE Trans. Dielectr. Electr. Insul., 24, 5, pp. 2828–2835 (2017).
(7) S. Kim, S.H. Jo, W. Kim, J. Park, J. Jeong, Y. Han et al., A semi-supervised autoencoder with an auxiliary task (SAAT) for power transformer fault diagnosis using dissolved gas analysis, IEEE Access, 8, pp. 178295–178310 (2020).
(8) Y. Cui, H. Ma, T. Saha, Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEBoost technique, IEEE Trans. Dielectr. Electr. Insul., 21, 5, pp. 2363–2373 (2014).
(9) G. Du, J. Zhang, M. Jiang, J. Long, Y. Lin, S. Li et al., Graph-based class-imbalance learning with label enhancement, IEEE Trans. Neural Netw. Learn. Syst., pp. 1–12 (2021).
(10) M. Koziarski, M. Woźniak, B. Krawczyk, Combined cleaning and resampling algorithm for multi-class imbalanced data with label noise, Knowl.-Based Syst., 204, pp. 1–12 (2020).
(11) S.M.A. Lopes, R.A. Flauzino, R.A.C. Altafim, Incipient fault diagnosis in power transformers by data-driven models with an over-sampled dataset, Electr. Power Syst. Res., 201, pp. 1–10 (2021).
(12) H.A. Illias, W.Z. Liang, Identification of transformer fault based on dissolved gas analysis using hybrid support vector machine-modified evolutionary particle swarm optimization, PLoS ONE, 13, 1, pp. 1–18 (2018).
(13) E. Li, L. Wang, B. Song, Fault diagnosis of power transformers with membership degree, IEEE Access, 7, pp. 28791–28798 (2019).
(14) S.I. Ibrahim, S.S.M. Ghoneim, I.B.M. Taha, DGALab: An extensible software implementation for DGA, IET Gener. Transm. Distrib., 12, 18, pp. 4117–4124 (2018).
(15) B. Zeng, J. Guo, W. Zhu, Z. Xiao, F. Yuan, S. Huang, A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM, Energies, 12, 21, pp. 1–10 (2019).
(16) G. Lv, H. Cheng, H. Zhai, L. Dong, Fault diagnosis of power transformer based on multi-layer SVM classifier, Electric Power Systems Research, 75, 1, pp. 9–15 (2005).
(17) M.S. Kraiem, F. Sánchez-Hernández, M.N. Moreno-García, Selecting the suitable resampling strategy for imbalanced data classification regarding dataset properties. An approach based on association models, Appl. Sci., 11, pp. 1–15 (2021).
(18) P. Babu, C. Columbus, S.R. Lakshmi, J. Chithambaram, Wind turbine fault modeling and classification using cuckoo-optimized modular neural networks, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg., 68, 4, pp. 369–374 (2023).
(19) A. Saidi, A. Draoui, T. Abdelouahed, Fault detection and diagnosis in photovoltaic power systems using Fisher random matrix approach, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg., 70, 4, pp. 513–518 (2025).
(20) K. Guerraiche, A.B. Abbou, L. Dekhici, Intelligent fault detection and location in electrical high-voltage transmission lines, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg., 69, 3, pp. 269–276 (2024).
(21) S. Saravanan, R.S. Kumar, P. Balakumar, Binary firefly algorithm-based reconfiguration for maximum power extraction under partial shading and machine learning approach for fault detection in solar PV arrays, Appl. Soft Comput., 154, pp. 1–15 (2024).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 REVUE ROUMAINE DES SCIENCES TECHNIQUES — SÉRIE ÉLECTROTECHNIQUE ET ÉNERGÉTIQUE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
