Application of physics-informed machine learning models for diagnosis of inter-turn short circuits in an induction motor

Cover Page

Cite item

Full Text

Abstract

Aim. To develop a physics-informed machine learning model capable of diagnosing inter-turn short circuits in the windings of squirrel-cage induction motors with high accuracy.

Materials and Methods. This study utilized a neural network training method using stator current data and FFT analysis, along with programming in Python and C++. A laboratory test bench was created to simulate the signs of inter-turn short circuits in the motor stator winding.

Results. A machine learning model capable of detecting inter-turn short circuits in the stator windings of induction motors with high accuracy was developed. The volume of labeled data required for model training was determined. A laboratory test bench was created to simulate inter-turn short circuits in the motor winding.

Conclusion. The obtained results allow us to address a number of issues associated with the effective use of neural networks for diagnosing induction motors, including the need for large volumes of data, low interpretability, poor generalization ability, and high sensitivity to the quality of the recorded data.

About the authors

Andrey S. Solovyov

Emperor Alexander I St. Petersburg State Transport University

Author for correspondence.
Email: vgvhyjh@mail.ru
ORCID iD: 0009-0001-2408-1840
SPIN-code: 1594-5049

post-graduate student

Russian Federation, St. Petersburg

Victor V. Nikitin

Emperor Alexander I St. Petersburg State Transport University

Email: pgups.emks@mail.ru
ORCID iD: 0000-0002-5699-0424
SPIN-code: 6864-5678

Dr. Sci. (Engineering), professor

Russian Federation, St. Petersburg

References

  1. Vainshtein RA. Additional losses in asynchronous motors with non-sinusoidal voltages. Saint-Petersburg: Energotech; 2020. (In Russ).
  2. Gromov LP, editor. The impact of power quality on the operation of electrical receivers. Novosibirsk: Nauka; 2022. (In Russ).
  3. Ryzhova EL, Kim KK, Ivanov SN. Evaluation оf Traction Motor Reliability Based On The State Of Winding Electrical Insulation. KnASTU Scientific Notes. 2023;5(69):8-14. (In Russ.). https://doi.org/10.17084/20764359-2023-69-8
  4. Kozjaruk AE, Vasilev BU, Shtop SA, Serdukov NA. Currents in bearings of induction motors of electric drives with semiconductor converter. In: 17th International Ural Conference on AC Electric Drives (ACED); 2018. Ekaterinburg; 1–5. https://doi.org/10.1109/ACED.2018.8341707
  5. Erdman JM, Kerkman RJ, Schlegel DW, Skibinski GL. Effect of PWM inverters on AC motor bearing currents and shaft voltages. IEEE Transactions on Industry Applications. 1996;32(2):250-259. https://doi.org/10.1109/28.491472
  6. Zhu W, De Gaetano D, Chen X, Jewell GW, Hu Y. A Review of Modeling and Mitigation Techniques for Bearing Currents in Electrical Machines with Variable-Frequency Drives. IEEE Access, 2022;10:125279-125297. https://doi.org/10.1109/ACCESS.2022.3225119
  7. Subrata Karmakar, Surajit Chattopadhyay, Madhuchhanda Mitra, Samarjit Sengupta. Induction Motor Fault Diagnosis. In: Power Systems. 2016. https://doi.org/10.1007/978-981-10-0624-1
  8. Podrezov NN, Gunin PA, Iliasova AS. Requirements for the qualifications of personnel for diagnostic monitoring at power engineering enterprises. Global Nuclear Safety. 2015;16(3):90–94. (In Russ). http://gns.mephi.ru/sites/default/files/journal/file/en.2015.3-11.pdf
  9. Villada F, Cadavid D, Munoz N, et al. Fault Diagnosis in Induction Motors Fed by PWM Inverters. In: 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED:229–234. https://doi.org/10.1109/DEMPED.2003.1234578
  10. Siddique A, Yadava G, Singh B. A review of stator fault monitoring techniques of induction motors. IEEE transactions on energy conversion. 2005;20(1):106–114. https://doi.org/10.1109/TEC.2004.837304
  11. Salnikov SV, Solodkiy EM, Vishnyakov DD, Iudin RY, Petrochenkov AB. Induction Motor Diagnosis Based on Machine Learning. In: XXVI International Conference on Soft Computing and Measurements (SCM), 2023. Saint Petersburg:210-214. https://doi.org/10.1109/SCM58628.2023.10159097
  12. Khalyasmaa A. Machine Learning as a Tool of High-Voltage Electrical Equipment Lifecycle Control Enhancement. Proceedings of Irkutsk State Technical University. 2020;24(5):1093-1094. (In Russ). https://doi.org/10.21285/1814-3520-2020-5-1093-1104
  13. Korobeinikov AB, Sarvarov AS. Analysis of Existing Methods for Diagnostics of Electric Motors and Perspectives of their Development. Electrotechnical Systems and Complexes. 2015;26(1):4-9. (In Russ). https://doi.org/10.18503/2311-8318
  14. Breiman L. Random Forests. Machine Learning. 2001;45(1):5-32. https://doi.org/10.1023/A:1010933404324
  15. Sereda EG, Solovyov AS. Asynchronous Motor Fault Detection Using Machine Learning Algorithms. Modern Transportation Systems and Technologies. 2025;11(2):261–272. https://doi.org/10.17816/transsyst682000
  16. Puja Pohakar, Ravi Gandhi, Surender Hans, Gulshan Sharma, Pitshou N. Bokoro. Analysis of multiple faults in induction motor using machine learning techniques. In: e-Prime – Advances in Electrical Engineering, Electronics and Energy. 2025; 12. 101007. https://doi.org/10.1007/s42369-025-00101-x
  17. Soloviev AS, Mikhailov MV, Nikitin VV, Kobzar EN. Fault Diagnosis of Induction Motors Based on Machine Learning: Approaches, Requirements and Current Trends. In: ElCon Conference of Young Researchers in Power, Energy & Industry Applications (ElCon-PEIA), 2026. Saint Petersburg, Russia:169-171. https://doi.org/10.1109/ElCon-PEIA69858.2026.11452073

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2026 Solovyov A.S., Nikitin V.V.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

link to the archive of the previous title