DETECTION OF POWER TRANSFORMER FAULTS USING DGA BASED ON COMBINED DUVAL PENTAGON AND ANN CLASSIFIERS
DOI:
https://doi.org/10.36801/k60kcd06Keywords:
Remove Dissolved Gas Analysis (DGA), DiagnosticsAbstract
Starting from the need to reduce the time required to analyze and detect power transformer faults, this article presents a software application specific to this topic, based on Artificial Neural Network (ANN) classifiers, in which the theoretical analysis method is Duval Combined Pentagons (DCP). The software application is based on algorithms implemented in Classification Learner from the MATLAB Statistics and Machine Learning toolbox. The classifiers' accuracy is optimized using Bayesian search, Grid search, and Random search. The developed software application was validated through several case studies, two of which were presented in comparison with the maintenance work performed.
References
(1) H. M. Avis, A. E. Lombard, V. Sibeko, “Predictive modelling based on transformer oil data for power system planning and operation,” 33rd Southern African Universities Power Engineering Conference (SAUPEC), Pretoria, South Africa, 2025, pp. 1-6.
(2) S. Nxumalo, L. Maluleka, S. Minhas, “The Effect of Dissolved Gases on the Breakdown Strength of Ester Transformer Oil,” 33rd Southern African Universities Power Engineering Conference (SAUPEC), Pretoria, South Africa, 2025, pp. 1-6.
(3) CIGRÉ Brochure 771 - Advances in DGA Interpretation, JWG D1/A2.47, July 2019, ISBN: 978-2-85873-473-3. CIGRE: Paris, France, 2019.
(4) Arnaud Nanfak, Eke Samuel, Issouf Fofana, Fethi Meghnefi, Martial Gildas Ngaleu, and Charles Hubert Kom, “Traditional fault diagnosis methods for mineral oil‐immersed power transformer based on dissolved gas analysis: Past, present, and future.” IET Nanodielectr. 2024; pp.1–34.
(5) H. Kalathiripi, V. Undety, P. S. Puhan, “Transformer Oil Analysis using DGA and UV-Visible Spectroscopy for Condition Monitoring,” International Conference on Sustainable Energy Technologies and Computational Intelligence (SETCOM), Gandhinagar, India, 2025, pp. 1-5
(6) ***IEEE Std C57.104™-2019 - Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers. Publication date: 01.11.2019. Electronic ISBN:978-1-5044-5973-0.
(7) ***CEI/IEC 60599:2022 - Mineral oil-impregnated electrical equipment in service – Guide to the interpretation of dissolved and free gas analysis. Publication date: 25.05.2022, Edition 4, pages 80.
(8) K. Helal, A. Maher, D. -E. A. Mansour, R. A. Abd El-aal, “Adaptation of the Duval Triangle for Enhanced Dissolved Gas Analysis and Diagnosis of Dielectric Nanofluids,” 25th International Middle East Power System Conference (MEPCON), Cairo, Egypt, 2024, pp. 1-5.
(9) N. Hirkaney and S. Lall, “Comparison of Fault Identification Methods for Analyzing Transformer Dissolved Gas,” 3rd International Conference on Energy, Power and Electrical Engineering (EPEE), Wuhan, China, 2023, pp. 902-907.
(10) L. Cheim, M. Duval, S. Haider, “Combined Duval Pentagons: A Simplified Approach.” in Energies, vol. 13, no. 11, pp. 1-12, June 2020.
(11) F. F. Selim, A. M. Azmy, M. A. Hassan, E. G. Atiya, “A Fuzzy Logic-based Methodology for Dissolved Gas Analysis to Enhance the Accuracy of Power Transformer Incipient Faults Detection,” 25th International Middle East Power System Conference (MEPCON), Cairo, Egypt, 2024, pp. 1-7.
(12) R. A. Prasojo, K. Diwyacitta, Suwarno, H. Gumilang, “Transformer paper condition assessment using Adaptive Neuro-Fuzzy Inference System model,” International Conference on Electrical Engineering and Computer Science (ICECOS), Palembang, Indonesia, 2017, pp. 237-242.
(13) F. Guerbas et al., “Neural Networks and Particle Swarm for Transformer Oil Diagnosis by Dissolved Gas Analysis,” in Scientific Reports, vol. 14, pp. 1-14, April 2024.
(14) M. A. Aljanobi and H. F. AlBinali, “State of the Art Machine Learning based DGA Analytical Solution,” IEEE PES 14th Asia-Pacific Power and Energy Engineering Conference (APPEEC), Melbourne, Australia, 2022, pp. 1-4.
(15) D. Saravanan, A. Hasan, A. Singh, H. Mansoor, R. N. Shaw, “Fault Prediction of Transformer Using Machine Learning and DGA," 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON), Greater Noida, India, 2020, pp. 1-5.
(16) A.-M. Aciu, M.-C. Nițu, C.-I. Nicola, M. Nicola, “Determining the Remaining Functional Life of Power Transformers Using Multiple Methods of Diagnosing the Operating Condition Based on SVM Classification Algorithms,” in Machines, vol. 12, no. 1, pp. 1-34, January 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ELECTRICAL MACHINES, MATERIALS AND DRIVES — PRESENT AND TRENDS
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
