Authors : Moma Munga Ferdinand; Lumanji Mbunga Luc; Mavungu Mayela Alain; Tshikudi Tshikudi Dennis

Volume/Issue : Volume 11 - 2026, Issue 10 - October

---

Google Scholar : https://tinyurl.com/mr4ymnhs

DOI : https://doi.org/10.38124/ijisrt/26Oct413

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Dissolved gas analysis (DGA) is the reference method for assessing the internal condition of oil-filled power transformers, and machine learning is increasingly used to interpret it. This article sets out, with consistent notation, the chain of concepts that links the physics of gas formation to the output of a supervised classifier and to an estimate of insulation life. It first formalises the thermochemical origin of fault gases (bond scission, Arrhenius kinetics, gas–oil partition) and the thermal ageing of cellulose (hot-spot temperature, ageing acceleration factor, loss of life).

Keywords : Dissolved Gas Analysis, Power Transformer, Arrhenius Law, Hot-Spot Temperature, Random Forest, Support Vector Machine, Stacking, Predictive Maintenance.

References :

1. Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., & Adda, M. (2022). On predictive maintenance in Industry 4.0: Overview, models, and challenges. Applied Sciences, 12(16), Article 8081. https://doi.org/10.3390/app12168081
2. Acikgoz, N., Sazli, M. H., & Kosalay, I. (2025). A comprehensive review of transformer fault diagnosis studies based on dissolved gas analysis: Classical methods, historical development of the devices used, artificial intelligence based methods, accuracy of classifications of predictions. Elektronika ir Elektrotechnika, 31(3), 4–21. https://doi.org/10.5755/j02.eie.39824
3. Behjat, V., Emadifar, R., Pourhossein, M., Rao, U. M., Fofana, I., & Najjar, R. (2021). Improved monitoring and diagnosis of transformer solid insulation using pertinent chemical indicators. Energies, 14(13), Article 3977. https://doi.org/10.3390/en14133977
4. Bilyaz, S., Bhati, A., Hamalian, M., Maynor, K., Soori, T., Gattozzi, A., Penney, C., Weeks, D., Xu, Y., Hu, L., Zhu, J. Y., Nelson, J. K., Hebner, R., & Bahadur, V. (2024). Modeling the impact of high thermal conductivity paper on the performance and life of power transformers. Heliyon, 10(6), Article e27783. https://doi.org/10.1016/j.heliyon.2024.e27783
5. Duanaputri, R., Prasojo, R. A., Wiranti, D., Wiwaha, S. S., Akbar, D. N., & Handani, G. P. C. (2023). Analysis and experiments of insulation loss of transformer kraft paper based on hotspot variations. International Journal of Electrical Engineering and Applied Sciences, 6(1). https://doi.org/10.54554/ijeeas.2023.6.01.004
6. International Electrotechnical Commission. (2022). Mineral oil-filled electrical equipment in service – Guidance on the interpretation of dissolved and free gases analysis (IEC 60599:2022, 4th ed.).
7. Leu, B., Serițan, G., & Enache, B. (2023). A new hybrid model to evaluate the loss of life of power transformers. Revue Roumaine des Sciences Techniques, Série Électrotechnique et Énergétique, 68(3), 277–282. https://doi.org/10.59277/RRST-EE.2023.3.5
8. Li, Y. (2023). The state of the art in transformer fault diagnosis with artificial intelligence and dissolved gas analysis: A review of the literature. arXiv. https://doi.org/10.48550/arXiv.2304.11880
9. Mienye, I. D., & Sun, Y. (2022). A survey of ensemble learning: Concepts, algorithms, applications, and prospects. IEEE Access, 10, 99129–99149. https://doi.org/10.1109/ACCESS.2022.3207287
10. Nanfak, A., Eke, S., Fofana, I., Meghnefi, F., Ngaleu, G. M., & Kom, C. H. (2024). Traditional fault diagnosis methods for mineral oil-immersed power transformer based on dissolved gas analysis: Past, present and future. IET Nanodielectrics. Advance online publication. https://doi.org/10.1049/nde2.12082
11. Rao, U. M., Fofana, I., Rajesh, K. N. V. P. S., & Picher, P. (2021). Identification and application of machine learning algorithms for transformer dissolved gas analysis. IEEE Transactions on Dielectrics and Electrical Insulation, 28(5), 1828–1835. https://doi.org/10.1109/TDEI.2021.009770
12. Taha, I. B. M., Ibrahim, S., & Mansour, D.-E. A. (2021). Power transformer fault diagnosis based on DGA using a convolutional neural network with noise in measurements. IEEE Access, 9, 111162–111170. https://doi.org/10.1109/ACCESS.2021.3102415
13. Zhang, Y., Tang, Y., Liu, Y., & Liang, Z. (2022). Fault diagnosis of transformer using artificial intelligence: A review. Frontiers in Energy Research, 10, Article 1006474. https://doi.org/10.3389/fenrg.2022.1006474