Abstract

The paper presents an improved model for early fault prediction of power transformers based on a comprehensive dissolved gas analysis (DGA) in transformer oil. The purpose of the study was to identify patterns of changes in the concentrations of hydrogen (H₂), methane (CH₄) and acetylene (C₂H₂) over time and to determine their diagnostic significance for the detection of thermal and electrical defects in the insulation system. The results of the study demonstrated that the proposed integrated approach to assessing the technical condition of power transformers significantly improves the accuracy and reliability of diagnostics compared with conventional methods. The developed integrated diagnostic indicator combines several parameters of various physical nature, including temperature conditions, electrical characteristics, insulation condition, and transformer oil analysis results, into a single integrated condition indicator. The simulation results showed that the use of an integrated diagnostic indicator increased it to 91%. The sensitivity was 0.89, and the F1-score was 0.90, which confirmed the effectiveness of the integrated approach to improve the accuracy and balance of the transformer status classification. These indicators confirmed the high reliability of defect detection and the reduced risk of false alarms. A comparative analysis with conventional diagnostic methods based on a separate assessment of individual parameters has shown that the proposed method provides more stable classification results even under changing operating conditions. The results obtained emphasised the practical significance of integrating statistical modelling, aggregation of multiparametric indicators, and analysis of gas dynamics into automated monitoring systems, which ultimately improves the quality of decision-making and the safety of operation of electric power systems

Keywords

dissolved gas analysis; DGA; early diagnosis; prediction of defects; insulation system; power system reliability

References

  1. Al-Sakini, S.R., Bilal, G.A., Sadiq, A.T., & Al-Maliki, W.A.K. (2025). Dissolved gas analysis for fault prediction in power transformers using machine learning techniques. Applied Sciences, 15(1), article number 118. doi: 10.3390/app15010118.
  2. Bessa, A.R., Fardin, J.F., Ciarelli, P.M., & Encarnação, L.F. (2023). Conventional dissolved gases analysis in power transformers: Review. Energies, 16(21), article number 7219. doi: 10.3390/en16217219.
  3. Bouchaoui, L., Hemsas, K.E., Mellah, H., & Benlahneche, S. (2021). Power transformer faults diagnosis using undestructive methods (Roger and IEC) and artificial neural network for dissolved gas analysis applied on the functional transformer in the Algerian north-eastern: A comparative study. Electrical Engineering & Electromechanics, 4, 3-11. doi: 10.20998/2074-272X.2021.4.01.
  4. CIGRE Working Group. (n.d.). Guide for transformer maintenance. Retrieved from https://www.academia.edu/15493047/Guide_for_Transformer_Maintenance_Guide_for_Transformer_Maintenance.
  5. Dai, J., Luo, B., Shen, X., Han, W., Cui, R., & Wu, J. (2025). A review of optical gas sensing technology for dissolved gas analysis in transformer oil. Frontiers in Physics, 13, article number 1547563. doi: 10.3389/fphy.2025.1547563.
  6. Dhini, A., Faqih, A., Kusumoputro, B., Surjandari, I., & Kusiak, A. (2020). Data-driven fault diagnosis of power transformers using dissolved gas analysis (DGA). International Journal of Technology, 11(2), 388-399. doi: 10.14716/ijtech.v11i2.3625.
  7. Duval, M. (2002). A review of faults detectable by gas-in-oil analysis in transformers. IEEE Electrical Insulation Magazine, 18(3), 8-17.
  8. Fofana, I. (2013). 50 years in the development of insulating liquids. IEEE Electrical Insulation Magazine, 29(5), 13-25. doi: 10.1109/MEI.2013.6585853.
  9. IEEE SA. (2019). IEEE guide for the interpretation of gases generated in mineral oil-immersed transformers. Retrieved from https://standards.ieee.org/ieee/C57.104/7476/.
  10. Islam, S.M., Wu, T., & Ledwich, G. (2000). A novel fuzzy logic approach to transformer fault diagnosis. IEEE Transactions on Dielectrics and Electrical Insulation, 7(2), 177-186. doi: 10.1109/94.841806.
  11. Jahromi, A.N., Piercy, R., Cress, S., Service, J., & Fan, W. (2009). An approach to power transformer asset management using health index. IEEE Transactions on Power Delivery, 25(2), 20-34. doi: 10.1109/MEI.2009.4802595.
  12. Kruger, M., Koch, M., Kraetge, A., & Rethmeier, K. (2008). New tools for diagnostic measurements on power transformers. In 2008 international conference on condition monitoring and diagnosis (pp. 488-491). Beijing: IEEE. doi: 10.1109/CMD.2008.4580332.
  13. Lai, J., Weng, D., Xian, F., Xie, Y., Chen, Y., Zhou, Q., & Yuan, C. (2026). A hybrid optimization model for transformer fault diagnosis based on gas classification. Digital, 6(1), article number 24. doi: 10.3390/digital6010024.
  14. Lv, X., Liu, F., Jiang, M., Zhang, F., & Jia, L. (2024). Fault diagnosis of power transformers based on dissolved gas analysis and improved LightGBM hybrid integrated model with dual-branch structure. IET Electric Power Applications, 18(12), 2008-2020. doi: 10.1049/elp2.12528.
  15. Nguyen, S.T., & Goetz, S. (2022). Dissolved gas analysis of insulating oil for power transformer fault diagnosis with Bayesian neural network. Smart Systems and Devices, 32(3), 61-68. doi: 10.51316/jst.160.ssad.2022.32.3.8.
  16. Prasojo, R.A., Sholehudin, M.F., Hanif, M.R., Nurhadi, S., & Joto, R. (2023). Case study and comparison of high voltage power transformer dissolved gas analysis assessed by different standards. International Journal of Frontier Technology and Engineering, 1(2), 63-74. doi: 10.33795/ijfte.v1i2.3215.
  17. Saha, T.K. (2003). Review of modern diagnostic techniques for assessing insulation condition in aged transformers. IEEE Transactions on Dielectrics and Electrical Insulation, 10(5), 903-917. doi: 10.1109/TDEI.2003.1237337.
  18. Sun, C., Zhou, Z., Zhang, Y., Jia, Z., & Huang, C. (2022). A dissolved gas assessment model for power transformers according to weighted association rule mining. Frontiers in Energy Research, 10, article number 879869. doi: 10.3389/fenrg.2022.879869.
  19. Tang, W.H., & Wu, Q.H. (2011). Condition monitoring and assessment of power transformers using computational intelligence. London: Springer. doi: 10.1007/978-0-85729-052-6.
  20. Thango, B.A. (2022). Dissolved gas analysis and application of artificial intelligence technique for fault diagnosis in power transformers: A South African case study. Energies, 15(23), article number 9030. doi: 10.3390/en15239030.
  21. Walker, C.M., Agarwal, V., & Al Rashdan, A.Y. (2022). Transformer health monitoring using dissolved gas analysis. International Journal of Prognostics and Health Management, 13(2). doi: 10.36001/ijphm.2022.v13i2.3141.
  22. Zhou, X., Tian, T., Liu, N., Bai, J., Luo, Y., Li, X., He, N., Zhang, P., & Jun, S. (2022). Research on gas production law of free gas in oil-immersed power transformer under discharge fault of different severity. Frontiers in Energy Research, 10, article number 1056604. doi: 10.3389/fenrg.2022.1056604.

Suggested citation

Chyngyzbek kyzy, Z., Begmatova, D., Tengizbaeva, N., Komiljonov, J., & Nurmatova, M. (2025). Model for early fault prediction based on transformer oil quality. News of Osh Technological University, 25(2), 43-52. https://doi.org/10.63621/notu./2.2025.43