AI-enabled Prediction of Power Transformer Remaining Useful Life Using Dissolved Gas Analysis and Random Forest Regression
DOI:
https://doi.org/10.54536/ajise.v5i1.6829Keywords:
Dissolved Gas Analysis, Power Transformers, Predictive Maintenance, Random Forest Regression, Remaining Useful LifeAbstract
Power transformers represent vital components within electrical power networks, and unexpected breakdowns can lead to significant financial losses and operational disruptions. Dissolved Gas Analysis remains a widely adopted technique for monitoring transformer health, yet most diagnostic methods and machine learning applications concentrate on fault identification rather than ongoing prognostic evaluation. Persistent challenges include the nonlinear nature of fault development, correlations among gas variables, and limited transparency in model outputs. This research introduces a data-driven framework designed to estimate transformer Remaining Useful Life through Dissolved Gas Analysis combined with an optimised Random Forest regression approach. The framework is validated using a publicly accessible dataset containing 2,100 labelled instances of dissolved gas readings, obtained from the Kaggle repository on transformer faults and Remaining Useful Life prediction. Statistical descriptors of hydrogen, carbon monoxide, acetylene, and ethylene are employed after targeted feature selection to address multicollinearity. Relative to traditional Dissolved Gas Analysis interpretation and baseline machine learning techniques, the proposed model achieves higher predictive accuracy, lower estimation error, and enhanced robustness. An analysis of feature importance further differentiates the framework by offering clear insight into the gas parameters most strongly associated with Remaining Useful Life. The findings substantiate the effectiveness of Random Forest regression in delivering dependable, interpretable, and practically applicable predictions of transformer service life.
Downloads
References
Aciu, A. M., Enache, S., & Nițu, M. C. (2024). A Reviewed Turn at of Methods for Determining the Type of Fault in Power Transformers Based On Dissolved Gas Analysis. Energies, 17(10), 1-26. https://doi.org/10.3390/en17102331.
Adekunle, A. A., Fofana, I., Picher, P., Rodriguez-Celis, E. M., Arroyo-Fernandez, O. H., Simard, H., & Lavoie, M. A. (2025). Multiclass Fault Diagnosis in Power Transformers Using Dissolved Gas Analysis and Grid Search-optimised Machine Learning. Energies, 18(13), 1-30. https://doi.org/10.3390/en18133535.
Bajwa, A., Tonoy, A. A. R., & Khan, M. A. M. (2025). IoT Enabled Condition Monitoring in Power Transformers: A Proposed Model. Review of Applied Science and Technology, 4(2), 118-144. https://doi.org/10.63125/3me7hy81.
Biradar, V., Kakeri, D., & Agasti, A. (2024). Machine Learning Based Predictive Maintenance in Distribution Transformers. In 8th International Conference on Computing, Communication, Control and Automation (pp. 1-5). https://doi:10.1109/ICCUBEA61740.2024.10774993.
David, O, Ebenezer, A., Bridget, M., Isaac, K. O., Andrew, Q., & Kwabena, A. K. (2023). Predictive Health Monitoring of a Power Transformer Using Machine Learning. Electrical and Electronic Engineering, 13(1), 12-18. http://doi:10.5923/j.eee.20231301.03.
Dladla, V. M., & Thango, B. A. (2025). Fault Classification in Power Transformers via Dissolved Gas Analysis and Machine Learning Algorithms: A Systematic Literature Review. Applied Sciences, 15(5), 1-43. https://doi.org/10.3390/app15052395.
Dubey, P. K., Singh, B, Patel, D. K., & Kumar, R. (2025). Review of Transformer Health Monitoring System and Fault Detection. International Journal of Sciences and Innovation Engineering, 2(6), 209-223. https://doi.org/10.70849/IJSCI.
El-Rashidy, N., Sultan, Y. A., & Ali, Z. H. (2025). Predicting Power Transformer Health Index And Life Expectation Based On Digital Twins and Multitask LSTM-GRU Model. Scientific Reports, 15(1), 1-29. https://doi.org/10.1038/s41598-024-83220-x.
Emme, S. S., & Moola, P. R. (2025). Application of Data Science Techniques and Machine Learning Based Classifiers for Transformer Health Assessment. Iraqi Journal of Science, 66(6), 2581-2592. https://doi.org/10.24996/ijs.2025.66.6.31.
Gao, Z., Yu, B., Guang, J., Jiang, S., Cong, X., Zhang, M., & Yu, L. (2025). Predicting the Remaining Service Life of Power Transformers Using Machine Learning. Processes, 13(11), 1-19. https://doi.org/10.3390/pr13113459.
Ibrahim, R. A., & Hebala, A. (2025). A Feature-Enhanced Approach to Dissolved Gas Analysis for Power Transformer Health Prediction Through Interpretable Ensemble Learning and Multi-model Evaluation. Technologies, 14(1), 1-30. https://doi.org/10.3390/technologies14010006.
Khan, M. A. M. (2025). AI and Machine Learning in Transformer Fault Diagnosis: A Systematic Review. American Journal of Advanced Technology and Engineering Solutions. 1(1), 290-318. http://dx.doi.org/10.2139/ssrn.5190585.
Liu, C., & Yang, W. (2025). Transformer Fault Diagnosis Using Machine Learning: A Method Combining SHAP Feature Selection and Intelligent Optimisation of LGBM. Energy Informatics, 8(52), 1-19. https://doi.org/10.1186/s42162-025-00519-3.
Liu, S., Xie, Z., & Hu, Z. (2025). DGA-based Fault Diagnosis Using Self-organising Neural Networks with Incremental Learning. Electronics, 14(3), 1-17. https://doi.org/10.3390/electronics14030424
Mashifane, L. D., Mendu, B., & Monchusi, B. B. (2025). State-of-the-Art Fault Detection and Diagnosis in Power Transformers: A Review of Machine Learning and Hybrid Methods. IEEE Access, 13(2), 48156-48172. https://doi: 10.1109/ACCESS.2025.3546861.
Radu, D. G., & Năvrăpescu, V. (2025). Optimising Energy Efficiency and Monitoring Methods for Power Transformers.” In International Aegean Conference on Electrical Machines and Power Electronics and International Conference on Optimisation of Electrical and Electronic Equipment (pp. 1-8). https://ieeexplore.ieee.org/document/11075283.
Shaqaq, S. A., & Alghadeer, A. A. (2025). Enhancing Power Transformer Reliability Through Real-Time Machine Learning Monitoring. In 15th International Conference on Power, Energy, and Electrical Engineering (pp. 22-25). https://ieeexplore.ieee.org/document/10987327.
Sintiya, E. S., Prasojo, A. R., & Hidayah, H. K. (2025). Application of Machine Learning for Predictive Maintenance in Power Transformer Health Assessment: A Comparative Study of Support Vector Machine, Artificial Neural Network, and Random Forest. In Proceeding International Seminar of Science and Technology (pp. 70-83). https://doi.org/10.33830/isst.v4i1.5233.
Velásquez, R. M. A. (2024). A Comprehensive Analysis for Wind Turbine Transformer and Its Limits in The Dissolved Gas Evaluation. Heliyon, 10(20), 1-24. https://doi.org/10.1016/j.heliyon.2024.e39449.
Yang, Y., & Wang, H. (2025). Random Forest-based Machine Failure Prediction: A Performance Comparison. Applied Sciences, 15(16), 1-22. https://doi.org/10.3390/app15168841.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Daniel Kumi Owusu, Curtis Ekow Baidoo
This work is licensed under a Creative Commons Attribution 4.0 International License.
