Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features
Inter-turn short-circuit (ITSC) faults in permanent magnet synchronous machines (PMSMs) present a significant reliability challenge in electric vehicle (EV) drivetrains, particularly under non-stationary operating conditions characterized by inverter-driven transients, variable loads, and magnetic s...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/15/4048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239803205255168 |
|---|---|
| author | Ádám Zsuga Adrienn Dineva |
| author_facet | Ádám Zsuga Adrienn Dineva |
| author_sort | Ádám Zsuga |
| collection | DOAJ |
| description | Inter-turn short-circuit (ITSC) faults in permanent magnet synchronous machines (PMSMs) present a significant reliability challenge in electric vehicle (EV) drivetrains, particularly under non-stationary operating conditions characterized by inverter-driven transients, variable loads, and magnetic saturation. Existing diagnostic approaches, including motor current signature analysis (MCSA) and wavelet-based methods, are primarily designed for steady-state conditions and rely on manual feature selection, limiting their applicability in real-time embedded systems. Furthermore, the lack of publicly available, high-fidelity datasets capturing the transient dynamics and nonlinear flux-linkage behaviors of PMSMs under fault conditions poses an additional barrier to developing data-driven diagnostic solutions. To address these challenges, this study introduces a simulation framework that generates a comprehensive dataset using finite element method (FEM) models, incorporating magnetic saturation effects and inverter-driven transients across diverse EV operating scenarios. Time-frequency features extracted via Discrete Wavelet Transform (DWT) from stator current signals are used to train a Transformer model for automated ITSC fault detection. The Transformer model, leveraging self-attention mechanisms, captures both local transient patterns and long-range dependencies within the time-frequency feature space. This architecture operates without sequential processing, in contrast to recurrent models such as LSTM or RNN models, enabling efficient inference with a relatively low parameter count, which is advantageous for embedded applications. The proposed model achieves 97% validation accuracy on simulated data, demonstrating its potential for real-time PMSM fault detection. Additionally, the provided dataset and methodology contribute to the facilitation of reproducible research in ITSC diagnostics under realistic EV operating conditions. |
| format | Article |
| id | doaj-art-3bcb8fcbca604ec68e3082bbcc68560a |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-3bcb8fcbca604ec68e3082bbcc68560a2025-08-20T04:00:50ZengMDPI AGEnergies1996-10732025-07-011815404810.3390/en18154048Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency FeaturesÁdám Zsuga0Adrienn Dineva1Department of Power Electronics and E-Drives, Audi Hungaria Faculty of Automotive Engineering, Széchenyi István University, 9026 Györ, HungaryDepartment of Power Electronics and E-Drives, Audi Hungaria Faculty of Automotive Engineering, Széchenyi István University, 9026 Györ, HungaryInter-turn short-circuit (ITSC) faults in permanent magnet synchronous machines (PMSMs) present a significant reliability challenge in electric vehicle (EV) drivetrains, particularly under non-stationary operating conditions characterized by inverter-driven transients, variable loads, and magnetic saturation. Existing diagnostic approaches, including motor current signature analysis (MCSA) and wavelet-based methods, are primarily designed for steady-state conditions and rely on manual feature selection, limiting their applicability in real-time embedded systems. Furthermore, the lack of publicly available, high-fidelity datasets capturing the transient dynamics and nonlinear flux-linkage behaviors of PMSMs under fault conditions poses an additional barrier to developing data-driven diagnostic solutions. To address these challenges, this study introduces a simulation framework that generates a comprehensive dataset using finite element method (FEM) models, incorporating magnetic saturation effects and inverter-driven transients across diverse EV operating scenarios. Time-frequency features extracted via Discrete Wavelet Transform (DWT) from stator current signals are used to train a Transformer model for automated ITSC fault detection. The Transformer model, leveraging self-attention mechanisms, captures both local transient patterns and long-range dependencies within the time-frequency feature space. This architecture operates without sequential processing, in contrast to recurrent models such as LSTM or RNN models, enabling efficient inference with a relatively low parameter count, which is advantageous for embedded applications. The proposed model achieves 97% validation accuracy on simulated data, demonstrating its potential for real-time PMSM fault detection. Additionally, the provided dataset and methodology contribute to the facilitation of reproducible research in ITSC diagnostics under realistic EV operating conditions.https://www.mdpi.com/1996-1073/18/15/4048inter-turn short circuit (ITSC)permanent magnet synchronous machine (PMSM)electric vehicles (EVs)fault detectionTransformer modeldiscrete wavelet transform (DWT) |
| spellingShingle | Ádám Zsuga Adrienn Dineva Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features Energies inter-turn short circuit (ITSC) permanent magnet synchronous machine (PMSM) electric vehicles (EVs) fault detection Transformer model discrete wavelet transform (DWT) |
| title | Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features |
| title_full | Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features |
| title_fullStr | Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features |
| title_full_unstemmed | Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features |
| title_short | Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features |
| title_sort | early detection of itsc faults in pmsms using transformer model and transient time frequency features |
| topic | inter-turn short circuit (ITSC) permanent magnet synchronous machine (PMSM) electric vehicles (EVs) fault detection Transformer model discrete wavelet transform (DWT) |
| url | https://www.mdpi.com/1996-1073/18/15/4048 |
| work_keys_str_mv | AT adamzsuga earlydetectionofitscfaultsinpmsmsusingtransformermodelandtransienttimefrequencyfeatures AT adrienndineva earlydetectionofitscfaultsinpmsmsusingtransformermodelandtransienttimefrequencyfeatures |