Hybrid Random Forest and Long Short-Term Memory based Transformer Fault Diagnostics and Prognostics

References

[1] A. Afolabi and O. Adeyemi, “Fuzzy-neural approach for transformer fault diagnosis in Nigeria,” International Journal of Electrical Power & Energy Systems, vol. 115, p. Article 105490, 2020

[2] A. Martinez and R. Garcia, “Practical implementation challenges of AI-based fault detection systems in operational environments,” Electric Power Systems Research, vol. 215, p. Article 108449, 2023.

[3] A. Olawale, I. Adebayo, and F. Olayinka, “SVM-PCA hybrid model for transformer fault diagnosis in Nigerian power grid,” Nigerian Journal of Technology, vol. 40, no. 4, pp. 678–689,

[4] A. Kumar and R. Patel, “Ensemble of CNNs for transformer vibration analysis and mechanical fault detection,” IEEE Transactions on Power Delivery, vol. 39, no. 3, pp. 1567–1578, 2024.

[5] A. Patel and M. Desai, “Random forest algorithms for transformer fault classification: An empirical study,” IEEE Transactions on Power Delivery, vol. 38, no. 2, pp. 789–800, 2023.

[6] A. Singh and G. Tiwari, “Shorted laminations in transformer cores and their impact on performance,” Journal of Electrical Engineering, vol. 54, no. 5, pp. 439–450, 2023.

[7] A. Singh and S. Kumar, “Impact of external faults on transformer health and detection methods,” Journal of Electrical Power and Energy Systems, vol. 122, pp. 567–579, 2023.

[8] C. Adebayo, G. Okengwu, Z. Mausi, and K. Zainab, “A decision-tree-based method for transformer fault diagnosis using dissolved gas analysis,” IEEE Transactions on Power Delivery, vol. 33, no. 2, pp. 904–912, 2018.

[9] D. Zhang, N. Zeng, and L. Lin, “Detection of Blades Damages in Aero Engine,” in 2020 Chinese Automation Congress (CAC), IEEE, Nov. 2020.

[10] C. Liu and W. Chen, “Transformer fault diagnosis using support vector machines and kernel principal component analysis,” Expert Systems with Applications, vol. 38, no. 5, pp. 6874–6881, 2011.

[11] D. Zou et al., “Power Transformer Fault Diagnosis Method Based on Machine Learning,” 2022 International Conference on Cyber-Physical Social Intelligence (ICCSI), pp. 484–491, 2022.

[12] E. Chinedu and C. Eze, “Hybrid decision tree-ANN model for transformer fault diagnostics in Nigerian substations,” Nigerian Journal of Technology, vol. 41, no. 3, pp. 567–578, 2022.

[13] F. Ojo and Q. Li, “Paper insulation aging in transformers: Effects of moisture and thermal stress,” Journal of Electrical Power Systems, vol. 131, no. 4, pp. 562–574, 2023.

[14] IEC (International Electrotechnical Commission), IEC 60599: Insulation-coordinated test methods for gas-filled transformers and reactors. 2015.

[15] I. G. Adebayo, K. L. Johnson, and R. T. Smith, “Identification method of inter-turn short circuit fault for distribution transformer based on power loss variation,” IEEE Transactions on Energy Conversion, vol. 37, no. 2, pp. 232–241, 2022, doi: 10.1109/TEC.2022.10184169.

[16] H. Lee and J. Park, “Random forests for transformer fault classification using electrical parameters,” Journal of Electrical Power Systems, vol. 127, no. 5, pp. 578–589, 2022.

[17] H. Wang and Y. Li, “Advances in dissolved gas analysis for transformer fault detection,” IEEE Transactions on Dielectrics and Electrical Insulation, vol. 30, no. 6, pp. 2345–2356, 2023.

[18] H. Zhao, Y. Liu, and Z. Wang, “An efficient hybrid PSO-ACO algorithm for power system restoration after blackout,” in Proceedings of the 2020 IEEE Power & Energy Society General Meeting (PESGM), IEEE, 2020, pp. 1–5.

[19] J. Brown, A. Smith, and R. Johnson, “Acoustic emission sensing for mechanical fault detection in power transformers,” IEEE Transactions on Power Delivery, vol. 37, no. 3, pp. 1789–1800, 2022. faults in transformers,” IEEE Transactions on Power Systems, vol. 39, no. 3, pp. 341–356, 2023.

[20] J. Liu, X. Chen, and Y. Wang, “Advanced dissolved gas analysis techniques for transformer fault detection,” IEEE Transactions on Dielectrics and Electrical Insulation, vol. 30, no. 4, pp. 1456–1467, 2023

@article{1707497,
      author = {Orji, Osita Lawrence, Ashigwuike Evans, Ejimofor Chijioke},
      title = {Hybrid Random Forest and Long Short-Term Memory based Transformer Fault Diagnostics and Prognostics},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {9},
      pages = {489-510},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707497.pdf},
      abstract = {This research presents the development and evaluation of a hybrid approach combining Random Forests (RF) and Long Short-Term Memory (LSTM) neural networks for transformer fault diagnostics and prognostics. The study aimed to leverage RF's capability in handling complex, high-dimensional data and LSTM's strength in capturing temporal dependencies to create a more robust and accurate system. The methodology involved comprehensive exploratory data analysis, individual implementation of RF and LSTM models, and their integration through both weighted average and stacked ensemble approaches. The results demonstrated that while the RF model achieved perfect classification accuracy (1.0000) and exceptional prognostic performance (R? = 0.9996, RMSE = 0.0189), the LSTM model showed strong classification capabilities (0.9656) but struggled with remaining useful life (RUL) prediction (R? = -30.0272). The final stacked ensemble hybrid model successfully combined the strengths of both approaches, achieving a fault classification accuracy of 0.940909 and remarkable RUL prediction metrics (R? = 0.999633, MAE = 4.807955 days). This performance significantly surpassed existing approaches in the field, including fuzzy-neural networks and PSO-optimised LSTM networks. The hybrid model demonstrated particular effectiveness in handling the unique challenges of the Nigerian power infrastructure, offering superior performance compared to previous models specifically developed for this context. The research concludes that the stacked ensemble architecture provides a comprehensive solution for transformer health management, successfully balancing high accuracy, computational efficiency, and interpretability. These findings have significant implications for practical maintenance planning and decision-making in power transformer operations.},
      keywords = {Random Forest (RF), Long Short Time Memory (LSTM), Artificial Neural Network (ANN), Direct Current (DC), Remaining Useful Life (RUL), Particle Swam Optimization (PSO)},
      month = {March},
  }