DATA FUSION BASED MULTIMODAL FAULT DIAGNOSIS IN PERMANENT MAGNET SYNCHRONOUS MOTORS

Merve Cömert; Evin Şahin Sadık; Abdurrahman Ünsal

doi:10.17780/ksujes.1723915

EN TR

DATA FUSION BASED MULTIMODAL FAULT DIAGNOSIS IN PERMANENT MAGNET SYNCHRONOUS MOTORS

Abstract

In this study, a deep learning-based method is proposed for the classification of inter-turn and inter-coil short circuit faults occurring in three-phase Permanent Magnet Synchronous Motors (PMSM). Three-phase current and vibration signals are used by multi-mode data fusion and a Convolutional Neural Networks (CNN) model. The spectrograms used as input in the CNN model are obtained using Short Time Fourier Transform (STFT). Using the proposed method, faults are classified with high accuracies (inter-turn faults with 100% accuracy, inter-coil faults with 98.95% accuracy). The obtained results show that the proposed multi-mode fusion approach provides high success in both fault detection and fault severity classification.

Keywords

DATA FÜZYON TABANLI ÇOK MODLU YÖNTEM İLE SABİT MIKNATISLI SENKRON MOTOR ARIZALARININ TESPİTİ

Öz

Bu çalışmada, üç fazlı Sabit Mıknatıslı Senkron Motorlarda (PMSM) meydana gelen iki temel stator arızası olan sarımlar arası (inter-turn) ve bobinler arası (inter-coil) kısa devre arızalarının sınıflandırılmasına yönelik derin öğrenme tabanlı bir yöntem önerilmiştir. Üç faz akım ve titreşim sinyalleri çok modlu veri füzyonu ve Evrişimli Sinir Ağları (CNN) ile kullanılarak sınıflandırma yapılmıştır. CNN modelinde girdi olarak kullanılan spektrogramlar Kısa Süreli Fourier Dönüşümü (STFT) kullanılarak elde edilmiştir. Önerilen yöntem ile arıza şiddetleri yüksek doğruluk oranı (inter-turn arızaları %100 doğrulukla, inter-coil arızaları %98.95 doğrulukla) ile sınıflandırılmıştır. Elde edilen sonuçlar, önerilen çok modlu füzyon yaklaşımının hem arıza tespitinde hem de arıza şiddeti sınıflandırılmasında yüksek başarı sunduğunu ortaya koymaktadır.

Anahtar Kelimeler

References

Al-Haddad, L. A., Jaber, A. A., Hamzah, M. N., & Fayad, M. A. (2024). Vibration-current data fusion and gradient boosting classifier for enhanced stator fault diagnosis in three-phase permanent magnet synchronous motors. Electrical Engineering, 106(3), 3253–3268. https://doi.org/10.1007/s00202-023-02148-z
Bayrak, A., Taştimur, C., & Akın, E. (2024). Diagnosis of permanent magnet assisted synchronous reluctance motor winding fault by convolutional neural network. Turkish Journal of Science and Technology, 19(2), 415–425. https://doi.org/10.55525/tjst.1463429
Canseven, H. T., & Ünsal, A. (2021, October 13–16). Performance improvement of fault-tolerant control for dual three-phase PMSM drives under inter-turn short circuit faults [Conference presentation]. IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, Toronto, ON, Canada. https://doi.org/10.1109/IECON48115.2021.9589578
Cinar, E. (2022). A sensor fusion method using transfer learning models for equipment condition monitoring. Sensors, 22(18), 6791. https://doi.org/10.3390/s22186791
Geetha, G., & Geethanjali, P. (2024). Optimal robust time‑domain feature based bearing fault and stator fault diagnosis. IEEE Open Journal of the Industrial Electronics Society, 5, 562–574. https://doi.org/10.1109/OJIES.2024.3417401
Gerlach, M. E., Zajonc, M., & Ponick, B. (2021). Mechanical stress and deformation in the rotors of a high‑speed PMSM and IM = Mechanischer Stress und Verformung in den Rotoren einer Hochdrehzahl‑PMSM und einer Hochdrehzahl‑IM. Elektrotechnik und Informationstechnik, 138(2), 96–109. https://doi.org/10.1007/s00502-021-00866-5
Gravina, R., Alinia, P., Ghasemzadeh, H., & Fortino, G. (2017). Multi‑sensor fusion in body sensor networks: State‑of‑the‑art and research challenges. Information Fusion, 35, 1339–1351. https://doi.org/10.1016/j.inffus.2016.09.005
Haddad, R. Z., Lopez, C. A., Foster, S. N., & Strangas, E. G. (2017). A voltage‑based approach for fault detection and separation in permanent magnet synchronous machines. IEEE Transactions on Industry Applications, 53(6), 5305–5314. https://doi.org/10.1109/TIA.2017.2726072

Jung, W., Yun, S. H., Lim, Y. S., Cheong, S., & Park, Y. H. (2023). Vibration and current dataset of three‑phase permanent magnet synchronous motors with stator faults. Data in Brief, 47, Article 108952. https://doi.org/10.1016/j.dib.2023.108952
Kibrete, F., Woldemichael, D. E., & Gebremedhen, H. S. (2024). Multi‑sensor data fusion in intelligent fault diagnosis of rotating machines: A comprehensive review. Measurement, 232, 114658. https://doi.org/10.1016/j.measurement.2024.114658
Li, L., Sun, S., Zeng, Y., Shi, Z., & Wang, X. (2023). An intelligent classification approach via multiple classifier fusion and its application to the fault diagnosis. IEEE Access, 11, 105040–105056. https://doi.org/10.1109/ACCESS.2023.3318319
van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605. http://www.jmlr.org/papers/v9/vandermaaten08a.html
Mohammad‑Alikhani, A., Jamshidpour, E., Dhale, S., Akrami, M., Pardhan, S., & Nahid‑Mobarakeh, B. (2025). Fault diagnosis of electric motors by a channel‑wise regulated CNN and differential of STFT. IEEE Transactions on Industry Applications, 61, 3066–3077. https://doi.org/10.1109/TIA.2025.3532556
Petrov, I., & Pyrhönen, J. (2013). Performance of low‑cost permanent magnet material in PM synchronous machines. IEEE Transactions on Industrial Electronics, 60(6), 2131–2138. https://doi.org/10.1109/TIE.2012.2191757
Tang, M., Liang, L., Zheng, H., Chen, J., & Chen, D. (2024). Anomaly detection of permanent magnet synchronous motor based on improved DWT‑CNN multi‑current fusion. Sensors, 24(8), 2553. https://doi.org/10.3390/s24082553
Wang, B., Feng, G., Huo, D., & Kang, Y. (2022). A bearing fault diagnosis method based on spectrum map information fusion and convolutional neural network. Processes, 10(7), Article 1426. https://doi.org/10.3390/pr10071426
Wang, J., Chen, Y., Liu, K., Zhu, Z.-Q., Wei, D., Zhou, S., … Luan, H. (2024). Multi-electrical signal analysis based bearing fault diagnosis for permanent magnet synchronous machines under uncertain controller bandwidths. IEEE Transactions on Energy Conversion, 39(4), 2514–2528. https://doi.org/10.1109/TEC.2024.3384955
Yu, G. (2019). A concentrated time–frequency analysis tool for bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 69(2), 371–381. https://doi.org/10.1109/TIM.2019.2901514
Yu, Y., & Gao, H. (2023, May). Rotor faults diagnosis in PMSMs based on branch current analysis and machine learning. In 2023 IEEE 6th International Electrical and Energy Conference (CIEEC) (pp. 1525–1530). IEEE. https://doi.org/10.1109/CIEEC58067.2023.10166472
Zhang, B., Chen, C., Wang, Y., & Li, J. (2024). STFT based CNN for interturn short circuit fault diagnosis of permanent magnet synchronous motor. In 2024 3rd International Symposium on Semiconductor and Electronic Technology (ISSET) (pp. 400–404). IEEE. https://doi.org/10.1109/ISSET62871.2024.10779733
Zhang, J., Wang, Y., Zhu, K., Zhang, Y., & Li, Y. (2021). Diagnosis of interturn short-circuit faults in permanent magnet synchronous motors based on few-shot learning under a federated learning framework. IEEE Transactions on Industrial Informatics, 17(12), 8495–8504. https://doi.org/10.1109/TII.2021.3067915
Zhao, J., Guan, X., Li, C., Mou, Q., & Chen, Z. (2021). Comprehensive evaluation of inter‑turn short circuit faults in PMSM used for electric vehicles. IEEE Transactions on Intelligent Transportation Systems, 22(1), 611–621. https://doi.org/10.1109/TITS.2020.2987637
Zhao, S., Chen, Y., Liang, F., Zhang, S., Shahbaz, N., Wang, S., … & Cheng, Y. (2024). Identifying early stator fault severity in DFIGs based on adaptive feature mode decomposition and multiscale complex component current trajectories. IEEE Transactions on Instrumentation and Measurement, 73, Article 1–16. https://doi.org/10.1109/TIM.2024.344334

Details

Primary Language

English

Subjects

Electrical Machines and Drives

Journal Section

Research Article

Authors

Merve Cömert
0000-0001-2345-6789
Türkiye

Evin Şahin Sadık ^*
0000-0002-2212-4210
Türkiye

Abdurrahman Ünsal
0000-0002-7053-517X
Türkiye

Publication Date

September 3, 2025

Submission Date

June 20, 2025

Acceptance Date

July 13, 2025

Published in Issue

Year 2025 Volume: 28 Number: 3

DOI

https://doi.org/10.17780/ksujes.1723915

IZ

https://izlik.org/JA36WX88KG

Cite

RIS / Bibtex

APA

Cömert, M., Şahin Sadık, E., & Ünsal, A. (2025). DATA FUSION BASED MULTIMODAL FAULT DIAGNOSIS IN PERMANENT MAGNET SYNCHRONOUS MOTORS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(3), 1546-1557. https://doi.org/10.17780/ksujes.1723915

Cited By

Fault Detection and Diagnosis for Multi‐Faults of PMSM‐Drive Systems Using a Hybrid Machine Learning Method

IET Power Electronics

https://doi.org/10.1049/pel2.70203