Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework
Bearing faults are a critical concern in electrical machines, particularly permanent magnet synchronous motors (PMSMs), commonly used in electric vehicles. Early and accurate classification of bearing fault severity is essential for predictive maintenance, as it enhances cost-effectiveness, ensures...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11082138/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421351662649344 |
|---|---|
| author | Korawege N. C. Jayasena Battur Batkhishig Babak Nahid-Mobarakeh Ali Emadi |
| author_facet | Korawege N. C. Jayasena Battur Batkhishig Babak Nahid-Mobarakeh Ali Emadi |
| author_sort | Korawege N. C. Jayasena |
| collection | DOAJ |
| description | Bearing faults are a critical concern in electrical machines, particularly permanent magnet synchronous motors (PMSMs), commonly used in electric vehicles. Early and accurate classification of bearing fault severity is essential for predictive maintenance, as it enhances cost-effectiveness, ensures safety, and extends product life. Although vibration-based monitoring offers rich diagnostic information, it remains costly and requires excess modifications. In contrast, current-based non-invasive techniques offer advantages in cost and integration but face challenges with accuracy due to operational complexities. This study presents six distinct artificial neural networks (ANNs)-based cascaded classification schemes for bearing fault severity classification. Discrete wavelet transform (DWT) with Symlet (Sym) is used for multi-resolution feature extraction in currents, combined with motor speed data to generate multi-channel features. These features are fed into an ANN-based level I algorithm using various fusion techniques, offering a more interpretable algorithmic framework. One approach employs a multi-input ANN for level I, integrated with an ANN-based level II for refined severity classification. This two-level cascaded approach achieves an accuracy over 99% on the Paderborn University dataset in various operational scenarios. The model is trained and analyzed using MATLAB. The proposed cascaded algorithms outperform single-stage models, and enhanced signal preprocessing improves accuracy and noise resilience. Additionally, the proposed risk-based performance indicator offers insights into maintenance strategies, while an optimum algorithm selection framework identifies an algorithm by considering a trade-off between computational complexity and accuracy. |
| format | Article |
| id | doaj-art-00364116add54f00ac53b82c697c8bad |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-00364116add54f00ac53b82c697c8bad2025-08-20T03:31:30ZengIEEEIEEE Access2169-35362025-01-011312967812970110.1109/ACCESS.2025.358975011082138Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded FrameworkKorawege N. C. Jayasena0https://orcid.org/0000-0001-7617-9412Battur Batkhishig1https://orcid.org/0000-0002-7002-2403Babak Nahid-Mobarakeh2https://orcid.org/0000-0003-3452-2731Ali Emadi3https://orcid.org/0000-0002-0676-1455Electrical and Computer Engineering Department, McMaster Automotive Resource Centre (MARC), McMaster University, Hamilton, CanadaElectrical and Computer Engineering Department, McMaster Automotive Resource Centre (MARC), McMaster University, Hamilton, CanadaElectrical and Computer Engineering Department, McMaster Automotive Resource Centre (MARC), McMaster University, Hamilton, CanadaElectrical and Computer Engineering Department, McMaster Automotive Resource Centre (MARC), McMaster University, Hamilton, CanadaBearing faults are a critical concern in electrical machines, particularly permanent magnet synchronous motors (PMSMs), commonly used in electric vehicles. Early and accurate classification of bearing fault severity is essential for predictive maintenance, as it enhances cost-effectiveness, ensures safety, and extends product life. Although vibration-based monitoring offers rich diagnostic information, it remains costly and requires excess modifications. In contrast, current-based non-invasive techniques offer advantages in cost and integration but face challenges with accuracy due to operational complexities. This study presents six distinct artificial neural networks (ANNs)-based cascaded classification schemes for bearing fault severity classification. Discrete wavelet transform (DWT) with Symlet (Sym) is used for multi-resolution feature extraction in currents, combined with motor speed data to generate multi-channel features. These features are fed into an ANN-based level I algorithm using various fusion techniques, offering a more interpretable algorithmic framework. One approach employs a multi-input ANN for level I, integrated with an ANN-based level II for refined severity classification. This two-level cascaded approach achieves an accuracy over 99% on the Paderborn University dataset in various operational scenarios. The model is trained and analyzed using MATLAB. The proposed cascaded algorithms outperform single-stage models, and enhanced signal preprocessing improves accuracy and noise resilience. Additionally, the proposed risk-based performance indicator offers insights into maintenance strategies, while an optimum algorithm selection framework identifies an algorithm by considering a trade-off between computational complexity and accuracy.https://ieeexplore.ieee.org/document/11082138/Artificial neural networks (ANNs)bearing fault severitycurrent signaturefeature fusioninterpretable artificial intelligencemultilevel cascaded framework |
| spellingShingle | Korawege N. C. Jayasena Battur Batkhishig Babak Nahid-Mobarakeh Ali Emadi Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework IEEE Access Artificial neural networks (ANNs) bearing fault severity current signature feature fusion interpretable artificial intelligence multilevel cascaded framework |
| title | Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework |
| title_full | Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework |
| title_fullStr | Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework |
| title_full_unstemmed | Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework |
| title_short | Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework |
| title_sort | current signature based bearing fault severity classification using a robust multilevel cascaded framework |
| topic | Artificial neural networks (ANNs) bearing fault severity current signature feature fusion interpretable artificial intelligence multilevel cascaded framework |
| url | https://ieeexplore.ieee.org/document/11082138/ |
| work_keys_str_mv | AT korawegencjayasena currentsignaturebasedbearingfaultseverityclassificationusingarobustmultilevelcascadedframework AT batturbatkhishig currentsignaturebasedbearingfaultseverityclassificationusingarobustmultilevelcascadedframework AT babaknahidmobarakeh currentsignaturebasedbearingfaultseverityclassificationusingarobustmultilevelcascadedframework AT aliemadi currentsignaturebasedbearingfaultseverityclassificationusingarobustmultilevelcascadedframework |