Fault Detection in Power Transformers Using Frequency Response Analysis and Machine Learning Models
Source abstract
Abstract
Power transformers are vital for maintaining the reliability and stability of electrical systems. However, their vulnerability to faults, such as partial discharges and winding deformation, poses significant operational risks. Advanced diagnostic techniques are essential for timely fault detection and predictive maintenance. This study investigates the application of machine learning (ML) techniques in transformer fault detection using Frequency Response Analysis (FRA) data. The study aims to evaluate the effectiveness of various ML models, the impact of frequency variations, and the contribution of numerical indices to fault classification accuracy. FRA data, comprising 50 to 70 measurements per transformer, were segmented into eight frequency bands (20 kHz to 12 MHz). A systematic approach utilizing a confusion matrix was applied to classify faults such as partial discharges and winding deformation. The performance of ML models, including Decision Trees and Subspace KNN, was assessed in terms of classification accuracy. Machine learning models achieved fault classification accuracies ranging from 80% to 100% across eight frequency bands (20 kHz to 12 MHz). Decision Tree models excelled in detecting insulation faults, achieving 100% accuracy for faults such as thermal aging (Class A), electrical stress (Class B), and moisture ingress (Class C). Subspace KNN models demonstrated strong performance for core-related faults, with classification accuracies of 100% for core displacement (Class B) and core buckling (Class C), but they faced challenges with lamination deformation, achieving 75% accuracy. Contamination-related faults exhibited a 100% False Negative Rate (FNR), indicating a need for model refinement. Fault detection was consistent across frequency bands, with key diagnostic markers at 7.6 MHz, 8.25 MHz, and 8.7 MHz providing high diagnostic value. Machine learning integration into FRA-based diagnostics enhances the accuracy and reliability of transformer fault detection. While current results are promising, future research should focus on deep learning approaches and enhanced feature extraction to address challenges such as data scarcity and fault diversity.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Power Transformer Diagnostics and Insulation · High voltage insulation and dielectric phenomena · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical & Electronic Engineering Technology, University of Johannesburg, Johannesburg 2092, South Africa
References (33)
Show source-provided references
1. Transfer function-based partial discharge localization in power transformers: A feasibility study10.1109/MEI.2002.1044318 ↗
2. Overview and Partial Discharge Analysis of Power Transformers: A Literature Review10.1109/ACCESS.2021.3075288 ↗
3. Catterson, V.M., McArthur, S.D.J., Moss, G., and Rudd, S.E. (2025, January 02). On-Line Transformer Condition Monitoring Through Diagnostics and Anomaly Detection. Available online: https://core.ac.uk/download/9028971.pdf.
4. Laayati, O., El Hadraoui, H., El Magharaoui, A., El-Bazi, N., Bouzi, M., Chebak, A., and Guerrero, J.M. (2022). An AI-Layered with Multi-Agent Systems Architecture for Prognostics Health Management of Smart Transformers: A Novel Approach for Smart Grid-Ready Energy Management Systems. Energies, 15.10.3390/en15197217 ↗
5. Islam, S.M., Coates, K.M., and Ledwich, G. (1997, January 5–9). Identification of high frequency transformer equivalent circuit using Matlab from frequency domain data. Proceedings of the Industry Applications Conference, 1997. Thirty-Second IAS Annual Meeting, IAS ’97, New Orleans, LA, USA. Conference Record of the 1997.
6. Figueroa, E.J. (2009, January 17–21). Managing an Aging Fleet of Transformers. Proceedings of the 6th Southern Africa Regional Conference, CIGRE, Cape Town, South Africa.
7. Geldenhuis, L.M. (2005, January 6–9). Power transformer life management. Proceedings of the CIRED 2005, 18th International Conference and Exhibition on Electricity Distribution, Turin, Italy.10.1049/cp:20050902 ↗
8. Islam, S.M., and Ledwich, G. (1996, January 6–19). Locating transformer faults through sensitivity analysis of high frequency modeling using transfer function approach. Proceedings of the 1996 IEEE International Symposium on Electrical Insulation, Montreal, QC, Canada.
9. Sherrington, I., Onsy, A., Rao, R., Brooks, H., and Philip, J. (2018, January 1). Condition Monitoring and Diagnostic Engineering Management. Proceedings of the 30th International Conference on Condition Monitoring and Diagnostic Engineering Management (COMADEM 2017), Preston, UK. Available online: https://core.ac.uk/download/161510444.pdf.
10. Power transformer health index and life span assessment: A comprehensive review of conventional and machine learning based approaches10.1016/j.engappai.2024.109474 ↗
11. Hashemnia, N., Abu-Siada, A., Masoum, M.A.S., and Islam, S.M. (2012, January 23–27). Characterization of transformer FRA signature under various winding faults. Proceedings of the 2012 IEEE International Conference on Condition Monitoring and Diagnosis, Bali, Indonesia.10.1109/CMD.2012.6416174 ↗
12. Transfer function method to diagnose axial displacement and radial deformation of transformer winding10.1109/MPER.2002.4312519 ↗
13. Improved power transformer winding fault detection using FRA diagnostics—Part 2: Radial deformation simulation10.1109/TDEI.2014.004592 ↗
14. Hashemnia, N., Abu-Siada, A., and Islam, S. (2013, January 21–25). Impact of axial displacement on power transformer FRA signature. Proceedings of the 2013 IEEE Power & Energy Society General Meeting, Vancouver, BC, Canada.10.1109/PESMG.2013.6672949 ↗
15. Shaban, A.E., Ibrahim, K.H., and Barakat, T.M. (2019, January 17–19). Modeling, Simulation and Classification of Power Transformer Faults Based on FRA Test. Proceedings of the 2019 21st International Middle East Power Systems Conference (MEPCON), Cairo, Egypt.10.1109/MEPCON47431.2019.9007984 ↗
16. Paleri, A., Preetha, P., and Sunitha, K. (2017, January 8–10). Frequency Response Analysis (FRA) in power transformers: An approach to locate inter-disk SC fault. Proceedings of the 2017 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Bangalore, India.10.1109/APPEEC.2017.8308951 ↗
17. Aljohani, O., and Abu-siada, A. (2016, January 5–9). Identification of the minimum detection of transformer bushing failure based on Frequency Response Analysis (FRA). Proceedings of the 2016 IEEE 2nd Annual Southern Power Electronics Conference (SPEC), Auckland, New Zealand.10.1109/SPEC.2016.7846058 ↗
18. Wang, S., Yang, F., Qiu, S., Zhang, N., Duan, N., and Wang, S. (2023, January 22–26). A New Classification Method for Radial Faults of Transformer Winding by FRA and PSO-RVM. Proceedings of the 2023 24th International Conference on the Computation of Electromagnetic Fields (COMPUMAG), Kyoto, Japan.10.1109/COMPUMAG56388.2023.10411777 ↗
19. Kuniewski, M., and Zydron, P. (2018, January 1–5). Analysis of the Applicability of Various Excitation Signals for FRA Diagnostics of Transformers. Proceedings of the 2018 IEEE 2nd International Conference on Dielectrics (ICD), Budapest, Hungary.10.1109/ICD.2018.8468391 ↗
20. A New Transformer FRA Measurement Technique to Reach Smart Interpretation for Inter-Disk Faults10.1109/TPWRD.2019.2909144 ↗
21. A New Interpretation of FRA Results by Sensitivity Analysis Method of Two FRA Measurement Connection Ways
22. Nurmanova, V., Akhmetov, Y., Bagheri, M., Zollanvari, A., Gharehpetian, G.B., and Phung, T. (2021, January 7–10). A New Transformer Winding RLC Model to Study the Effect of the Disk Space Variation on FRA Signature. Proceedings of the 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Bari, Italy.10.1109/EEEIC/ICPSEurope51590.2021.9584786 ↗
23. Shintemirov, A. (2013, January 13–17). Modelling of power transformer winding faults for interpretation of frequency response analysis (FRA) measurements. Proceedings of the 4th International Conference on Power Engineering, Energy and Electrical Drives, Istanbul, Turkey.10.1109/PowerEng.2013.6635810 ↗
24. Al-Ameri, S.M., Alawady, A.A., Kamarudin, M.S., Yousof, M.F.M., Abdul-Malek, Z., and Salem, A.A. (2022, January 25–26). Understanding Power Transformer Frequency Response Based on Model Simulation. Proceedings of the 2022 2nd International Conference on Emerging Smart Technologies and Applications (eSmarTA), Ibb, Yemen.10.1109/eSmarTA56775.2022.9935426 ↗
25. Cheng, B., Crossley, P., Wang, Z., Jarman, P., and Fieldsend-Roxborough, A. (2019, January 7–10). Interpretation of FRA Results through Low Frequency Transformer Modelling. Proceedings of the 2019 2nd International Conference on Electrical Materials and Power Equipment (ICEMPE), Guangzhou, China.10.1109/ICEMPE.2019.8727328 ↗
26. Classifying Transformer Winding Deformation Fault Types and Degrees Using FRA Based on Support Vector Machine10.1109/ACCESS.2019.2932497 ↗
27. Trela, K., and Gawrylczyk, K.M. (2018, January 9–12). Frequency response modeling of power transformer windings considering the attributes of ferromagnetic core. Proceedings of the 2018 International Interdisciplinary PhD Workshop (IIPhDW), Świnouście, Poland.10.1109/IIPHDW.2018.8388328 ↗
28. Wang, S., Wang, S., Qiu, H., Feng, H., Wang, S., and Abu-Siuda, A. (2018, January 23–26). Frequency Response Analysis of the Transformer Subjected to Twice Short-circuit Impulse Tests Under Two Different Connection Schemes. Proceedings of the 2018 Condition Monitoring and Diagnosis (CMD), Perth, WA, Australia.10.1109/CMD.2018.8535767 ↗
29. Alsuhaibani, S.H., Khan, Y., and Malik, N.H. (2018, January 15). Frequency Response Analysis of Medium Voltage Distribution Transformer. Proceedings of the 2018 1st International Conference on Advanced Research in Engineering Sciences (ARES), Dubai, United Arab Emirates.10.1109/ARESX.2018.8723279 ↗
30. Pham, D.A.K., Pham, T.M.T., Safari, M.H., Ho, V.N.C., Borsi, H., and Gockenbach, E. (2012, January 17–20). FRA-based transformer parameters at low frequencies. Proceedings of the 2012 International Conference on High Voltage Engineering and Application, Shanghai, China.10.1109/ICHVE.2012.6357083 ↗
31. Nurmanova, V., Akhmetov, Y., Bagheri, M., Zollanvari, A., Gharehpetian, G.B., and Phung, T. (2020, January 9–12). A New Transformer FRA Test Setup for Advanced Interpretation and Winding Short-circuit Prediction. Proceedings of the 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Madrid, Spain.10.1109/EEEIC/ICPSEurope49358.2020.9160545 ↗
32. Muthukuda, D., Ranasinghe, P., Morapitiya, P., Fernando, M., Wijayakulasooriya, J., and Bandara, K. (2023, January 25–26). AI Approach for FRA Based Condition Assessment of Power Transformers. Proceedings of the 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), Peradeniya, Sri Lanka.10.1109/ICIIS58898.2023.10253506 ↗
33. Wang, S., Yuan, Z., and Wang, S. (2021, January 15–17). The Comparison of Nodal Voltage Matrix and State Space Methods for Calculating the FRA Curve of the Transformer Winding. Proceedings of the 2021 International Conference on Advanced Electrical Equipment and Reliable Operation (AEERO), Beijing, China.10.1109/AEERO52475.2021.9708319 ↗