International Journal of Engineering
Trends and Technology

Research Article | Open Access | Download PDF
Volume 74 | Issue 10 | Year 2026 | Article Id. IJETT-V74I10P124 | DOI : https://doi.org/10.14445/22315381/IJETT-V74I10P124

Predictive Maintenance of Power Transformers: A Thermodynamic Fuzzy Logic Approach for Severely Imbalanced DGA Data

Jorge Luis Cordova Santos, Jezzy James Huaman Rojas

Received Revised Accepted Published
13 May 2026 10 Sep 2026 16 Sep 2026 27 Oct 2026

Citation :

Jorge Luis Cordova Santos, Jezzy James Huaman Rojas, "Predictive Maintenance of Power Transformers: A Thermodynamic Fuzzy Logic Approach for Severely Imbalanced DGA Data," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 339-351, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P124

Abstract

The ageing power transformer is one of the most important components of an electrical transmission grid, and it is important that diagnostic tools can be developed that can be applied in the field for reliable identification of faults when there is a significant data imbalance. In this paper, a new predictive maintenance model is introduced that combines Reliability, Availability, Maintainability and Safety (RAMS) engineering with Weibull parametric distributions to model combustible gas evolution within the normative limits of the IEEE C57.104-2019 standard. A forced-zero-probability matrix is introduced into the data generation pipeline so that all concentration ratios generated are within the thermodynamic plausibility range, which helps to overcome the thermodynamic implausibility that arises when using conventional oversampling algorithms like SMOTE. A Mamdani Fuzzy Inference System (FIS) was applied to evaluate all 2,000 synthetic DGA profiles, including 60 ground-truth critical fault cases (3.00%) deterministically injected to stress-test diagnostic boundary conditions. The framework achieved a 100% high-priority capture rate: all 60 ground-truth critical cases were classified into intervention-required states (39 as 'Critical' and 21 as 'Poor'), and no false 'Critical' alarm was recorded among the 1,940 non-injected records. Control-surface analysis verified Ethylene (C2H4) and Acetylene (C2H2) as the main reasons for Health Index appraisal, and directly indicated known high-energy degradation mechanisms. By maintaining complete end-to-end mathematical traceability, this architecture provides grid operators with an interpretable, standard-compliant predictive tool that resolves the operational opacity of black-box models.

Keywords

Dissolved Gas Analysis, Fuzzy logic, Predictive maintenance, RAMS engineering, Reliability modeling.

References

  1. Ryad Zemouri, “Power Transformer Prognostics and Health Management using Machine Learning: A Review and Future Directions,” Machines, vol. 13, no. 2, pp. 1-29, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  2. Wei Huang et al., “Modeling the Aging-Dependent Reliability of Transformers Considering the Individualized Aging Threshold and Lifetime,” IEEE Transactions on Power Delivery, vol. 37, no. 6, pp. 4631-4645, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  3. Aman Samson Mogos, Xiaodong Liang, and C.Y. Chung, “Enhancing Transformer Health Index Prediction using Dissolved Gas Analysis Data Through Integration of LightGBM and Robust EM Algorithms,” IEEE Access, vol. 12, pp. 108472-108483, 2024.
    [CrossRef] [Google Scholar] [Publisher Link] 
  4. Cheng Liu, and Weiming Yang, “Transformer Fault Diagnosis using Machine Learning: A Method Combining SHAP Feature Selection and Intelligent Optimization of LGBM,” Energy Informatics, vol. 8, no. 1, pp. 1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link] 
  5. Yan Zhang et al., “Fault Diagnosis of Transformer using Artificial Intelligence: A Review,” Frontiers in Energy Research, vol. 10, pp. 1-10, 2022.
    [CrossRef] [Google Scholar] [Publisher Link] 
  6. Youngjin Han, and Inwhee Joe, “Enhancing Machine Learning Models through PCA, SMOTE-ENN, and Stochastic Weighted Averaging,” Applied Sciences, vol. 14, no. 21, pp. 1-22, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  7. Muhammad Farhan Naeem et al., “A Novel Method for Life Estimation of Power Transformers using Fuzzy Logic Systems: An Intelligent Predictive Maintenance Approach,” Frontiers in Energy Research, vol. 10, pp. 1-20, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  8. Vasiliki Vita et al., “Predictive Maintenance for Distribution System Operators in Increasing Transformers’ Reliability,” Electronics, vol. 12, no. 6, pp. 1-23, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  9. Maryam Assafo et al., “On the Stability and Homogeneous Ensemble of Feature Selection for Predictive Maintenance: A Classification Application for Tool Condition Monitoring in Milling,” Sensors, vol. 23, no. 9, pp. 1-39, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  10. Milad Soleimani, Mladen Kezunovic, and Sergiy Butenko, “Linear Arrhenius-Weibull Model for Power Transformer Thermal Stress Assessment,” IEEE Access, vol. 10, pp. 20023-20032, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  11. Muhammad Ilham Chaniago, P. Purwoharjono, and Rudy Gianto, “Transformer Reliability Analysis using the Weibull Distribution Method (Case Study of the Power Transformer at the Kota Baru Pontianak Substation),” Telecommunications, Computers, and Electricals Engineering Journal (TELECTRICAL), vol. 2, no. 2, pp. 247-259, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  12. IEEE Std C57.104-2019, IEEE Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers, IEEE Standards Association 2019. [Online]. Available: https://standards.ieee.org/ieee/C57.104/7476/
  13. Yan Huo, Diyuan Guan, and Lingyan Dong, “Intelligent Fault Diagnosis of Unbalanced Samples using Optimized Generative Adversarial Network,” Applied Sciences, vol. 14, no. 11, pp. 1-19, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  14. Sahar R. Al-Sakini et al., “Dissolved Gas Analysis for Fault Prediction in Power Transformers using Machine Learning Techniques,” Applied Sciences, vol. 15, no. 1, pp. 1-23, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  15. Shuaibing Li et al., “Review of Transformer Health Index from the Perspective of Survivability and Condition Assessment,” Electronics, vol. 12, no. 11, pp. 1-24, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  16. Moamin A. Mahmoud et al., “The Current State of the Art in Research on Predictive Maintenance in Smart Grid Distribution Network: Fault's Types, Causes and Prediction Methods - A Systematic Review,” Energies, vol. 14, no. 16, pp. 1-27, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  17. Xinyao Li et al., “Domain Adaptive Remaining Useful Life Prediction with Transformer,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  18. Muhammad Akmal A. Putra, Suwarno, and Rahman Azis Prasojo, “Improving Transformer Health Index Prediction Performance using Machine Learning Algorithms with a Synthetic Minority Oversampling Technique,” Energies, vol. 18, no. 9, pp. 1-44, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  19. Md. Nuruzzaman et al., “Predictive Maintenance in Power Transformers: A Systematic Review of AI and IoT Applications,” ASRC Procedia: Global Perspectives in Science and Scholarship, vol. 1, no. 1, pp. 34-47, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  20. Samuel Lessinger et al., “Aging Assessment of Power Transformers with Data Science,” Energies, vol. 18, no. 15, pp. 1-33, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  21. Eun Hui Ko, Tatjana Dokic, and Mladen Kezunovic, “Prediction Model for the Distribution Transformer Failure using Correlation of Weather Data,” 5th International Colloquium on Transformer Research and Asset Management, Springer, Singapore, vol. 671, pp. 135-144, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  22. Zhaoyi Xu, and Joseph Homer Saleh, “Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities,” Reliability Engineering and System Safety, vol. 211, pp. 1-16, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  23. Siqi Liu, Zhiyuan Xie, and Zhengwei Hu, “DGA-based Fault Diagnosis using Self-Organizing Neural Networks with Incremental Learning,” Electronics, vol. 14, no. 3, pp. 1-17, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  24. Muhammad Mujahid et al., “Data Oversampling and Imbalanced Datasets: An Investigation of Performance for Machine Learning and Feature Engineering,” Journal of Big Data, vol. 11, no. 1, pp. 1-32, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  25. P.C.K. Guri, and Krste Najdenkoski, “Transformer Remaining Life Calculation based on Degree of Polymerization (DP),” Journal of Multidisciplinary Engineering Science and Technology (JMEST), vol. 4, no. 11, pp. 16779-16786, 2024.
    [Google Scholar]