Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models

Sule Ozturk; Ali Osman Arslan; Osman Bilgin

doi:10.17798/bitlisfen.1746052

Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models

Abstract

Permanent magnet synchronous motors (PMSMs) have become commonly employed in various critical applications such as industrial automation, electric vehicles, aerospace, robotics, and HVAC/R systems. In this study, the detection of rotor magnet breakage faults in PMSMs was investigated using two artificial intelligence (AI) techniques: Multilayer Perceptron (MLP) and Support Vector Machine (SVM). Fault conditions were experimentally induced by introducing controlled breaks in the rotor magnets of PMSM samples. Stator current signals were collected using a current probe and oscilloscope, then preprocessed to remove noise components. Fast Fourier Transform (FFT) was applied to convert the time-domain signals into the frequency domain, allowing extraction of characteristic fault-related features. These frequency spectrum features served as inputs to train and test the MLP and SVM classifiers. Both AI models achieved high classification accuracy in distinguishing healthy and faulty motor states, with overall accuracies exceeding 95%. Comparative analysis showed that while both models performed effectively, the SVM demonstrated slightly superior precision in fault detection. The proposed approach confirms that frequency-domain analysis combined with AI classification provides a reliable, non-invasive method for timely detection of rotor magnet faults in PMSMs, which is crucial for improving system reliability and minimizing unexpected downtime.

Keywords

Ethical Statement

There is no conflict of interest between the authors.

Thanks

This article is derived from the author’s master’s thesis.

References

R. G. Shriwastava, M. B. Diagavane, and S. R. Vaishnav, "Literature Review of Permanent Magnet AC Motors Drive for Automotive Application," Buletin Teknik Elektro Dan Informatika (Bulletin of Electrical Engineering and Informatics), vol. 1, pp. 7–14, 2012.
S. Saha and U. Kar, "Signal-Based Position Sensor Fault Diagnosis Applied to PMSM Drives for Fault-Tolerant Operation in Electric Vehicles," World Electric Vehicle Journal, vol. 14, 2023. https://doi.org/10.3390/wevj14050123.
Md. Y. Ali Khan, "A Review of Analysis and Existing Simulation Model of Three Phase Permanent Magnet Synchronous Motor Drive (PMSM)," Control Systems and Optimization Letters, vol. 2, pp. 349–56, 2024. https://doi.org/10.59247/csol.v2i3.151.
P. Pietrzak and M. Wolkiewicz, "Application of continuous wavelet transform and convolutional neural networks in fault diagnosis of PMSM stator windings," Bulletin of the Polish Academy of Sciences Technical Sciences, pp. 150202–150202, 2024. https://doi.org/10.24425/bpasts.2024.150202.
Z. Wang, J. Yang, H. Ye, and W. Zhou, "A review of permanent magnet synchronous motor fault diagnosis," in IEEE Transportation Electrification Conference and Expo, ITEC Asia-Pacific 2014 - Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., 2014. https://doi.org/10.1109/ITEC-AP.2014.6940870.
Z. Ullah, B. A. Lodhi, and J. Hur, "Detection and identification of demagnetization and bearing faults in PMSM using transfer learning-based VGG," Energies (Basel), vol. 13, 2020. https://doi.org/10.3390/en13153834.
A. Sergakis, M. Salinas, N. Gkiolekas, and K. N. Gyftakis, "A Review of Condition Monitoring of Permanent Magnet Synchronous Machines: Techniques, Challenges and Future Directions," Energies (Basel), vol. 18, 2025. https://doi.org/10.3390/en18051177.
O. Salhi, B. Mabrouk, B. Amghar, and C. Ben Njima, "Innovative ISF Fault Detection in PMSMs Using FFT and Artificial Intelligence Techniques," EasyChair Preprint, 2025.

K. Lv, D. Wang, W. Huang, H. Liu, Y. Jiang, and J. Hu, "Multiple Fault Diagnosis of PMSM Based on Stator Tooth Flux and Parallel Residual Convolutional Neural Network," IEEE Transactions on Transportation Electrification, 2024. https://doi.org/10.1109/TTE.2024.3349616.
H. Li, Z. Q. Zhu, Z. Azar, R. Clark, and Z. Wu, "Fault Detection of Permanent Magnet Synchronous Machines: An Overview," Preprints, 2024. https://doi.org/10.20944/preprints202412.1988.v1.
P. Pietrzak and M. Wolkiewicz, "Fault Diagnosis of PMSM Stator Winding Based on Continuous Wavelet Transform Analysis of Stator Phase Current Signal and Selected Artificial Intelligence Techniques," Electronics (Switzerland), vol. 12, 2023. https://doi.org/10.3390/electronics12071543.
M. El-Dalahmeh, M. Al-Greer, I. Bashir, M. El-Dalahmeh, A. Demirel, and O. Keysan, "Autonomous fault detection and diagnosis for permanent magnet synchronous motors using combined variational mode decomposition, the Hilbert-Huang transform, and a convolutional neural network," Computers and Electrical Engineering, vol. 110, 2023. https://doi.org/10.1016/j.compeleceng.2023.108894.
Y. Yu, Y. Li, D. Zeng, Y. Hu, and J. Yang, "Permanent magnet synchronous motor demagnetization fault diagnosis and localization," IEEE Sensors Journal, 2025. https://doi.org/10.1109/JSEN.2025.3561192.
Y. Yu, Y. Li, D. Zeng, Y. Hu, and J. Yang, "Permanent magnet synchronous motor demagnetization fault diagnosis based on PCA-ISSA-PNN," Scientific Reports, vol. 14, p. 21921, 2024. https://doi.org/10.1038/s41598-024-72596-5.
Y. Chen, S. Liang, W. Li, H. Liang, and C. Wang, "Faults and diagnosis methods of permanent magnet synchronous motors: A review," Applied Sciences (Switzerland), vol. 9, 2019. https://doi.org/10.3390/app9102116.
J. A. Rosero, J. Cusido, A. Garcia, J. A. Ortega, and L. Romeral, "Broken bearings and eccentricity fault detection for a permanent magnet synchronous motor," in IECON Proceedings (Industrial Electronics Conference), 2006, pp. 964–9. https://doi.org/10.1109/IECON.2006.347599.
M. Karami, N. Mariun, M. R. Mehrjou, M. Z. A. Ab Kadir, N. Misron, and M. A. Mohd Radzi, "Diagnosis of static eccentricity fault in line start permanent magnet synchronous motor," in Conference Proceeding - 2014 IEEE International Conference on Power and Energy, PECon 2014, Institute of Electrical and Electronics Engineers Inc., 2014, pp. 83–6. https://doi.org/10.1109/PECON.2014.7062418.
Z. Ullah, J. H. Im, and S. Ahmed, "Detection and Separation of Faults in Permanent Magnet Synchronous Machines using Hybrid Fault-Signatures," in 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022, Institute of Electrical and Electronics Engineers Inc., 2022. https://doi.org/10.1109/ECCE50734.2022.9947448.
P. Pietrzak and M. Wolkiewicz, "Machine Learning-Based Stator Current Data-Driven PMSM Stator Winding Fault Diagnosis," Sensors, vol. 22, 2022. https://doi.org/10.3390/s22249668.
J. W. Cooley and J. W. Tukey, "An Algorithm for the Machine Calculation of Complex Fourier Series," Mathematics of Computation, vol. 19, p. 297, 1965. https://doi.org/10.2307/2003354.
N. Mehala and R. Dahiya, "A Comparative Study of FFT, STFT and Wavelet Techniques for Induction Machine Fault Diagnostic Analysis," 2008. https://doi.org/10.5555/1569508.1569542.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, pp. 533–6, 1986. https://doi.org/10.1038/323533a0.
C. Cortes, V. Vapnik, and L. Saitta, "Support-Vector Networks," Machine Learning, vol. 20, Kluwer Academic Publishers, 1995. https://doi.org/10.1007/BF00994018.
S. Benkaihoul, L. Mazouz, T. T. Naas, Ö. Yildirim, and R. D. Mohammedi, "BROKEN MAGNETS FAULT DETECTION IN PMSM USING A CONVOLUTIONAL NEURAL NETWORK AND SVM," Journal of Engineering and Technology for Industrial Applications ITEGAM-JETIA Manaus, vol. 48, pp. 57–64, 2024. https://doi.org/10.5935/jetia.v10i48.1185.

Details

Primary Language

English

Subjects

Electrical Machines and Drives

Journal Section

Research Article

Authors

Sule Ozturk ^*
0009-0006-4815-8300
Türkiye

Ali Osman Arslan
0000-0003-4097-9754
Türkiye

Osman Bilgin
0000-0002-4576-0113
Türkiye

Publication Date

December 31, 2025

Submission Date

July 18, 2025

Acceptance Date

September 27, 2025

Published in Issue

Year 2025 Volume: 14 Number: 4

DOI

https://doi.org/10.17798/bitlisfen.1746052

IZ

https://izlik.org/JA75RK38KM

Cite

RIS / Bibtex

APA

Ozturk, S., Arslan, A. O., & Bilgin, O. (2025). Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 14(4), 2456-2475. https://doi.org/10.17798/bitlisfen.1746052

AMA

1.Ozturk S, Arslan AO, Bilgin O. Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2025;14(4):2456-2475. doi:10.17798/bitlisfen.1746052

Chicago

Ozturk, Sule, Ali Osman Arslan, and Osman Bilgin. 2025. “Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 14 (4): 2456-75. https://doi.org/10.17798/bitlisfen.1746052.

EndNote

Ozturk S, Arslan AO, Bilgin O (December 1, 2025) Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 14 4 2456–2475.

IEEE

[1]S. Ozturk, A. O. Arslan, and O. Bilgin, “Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 14, no. 4, pp. 2456–2475, Dec. 2025, doi: 10.17798/bitlisfen.1746052.

ISNAD

Ozturk, Sule - Arslan, Ali Osman - Bilgin, Osman. “Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 14/4 (December 1, 2025): 2456-2475. https://doi.org/10.17798/bitlisfen.1746052.

JAMA

1.Ozturk S, Arslan AO, Bilgin O. Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2025;14:2456–2475.

MLA

Ozturk, Sule, et al. “Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 14, no. 4, Dec. 2025, pp. 2456-75, doi:10.17798/bitlisfen.1746052.

Vancouver

1.Sule Ozturk, Ali Osman Arslan, Osman Bilgin. Fault Diagnosis of Broken Rotor Magnets in PMSMS Using FFT Features and Machine Learning: MLP and SVM Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2025 Dec. 1;14(4):2456-75. doi:10.17798/bitlisfen.1746052