A Siamese Vision Transformer for Bearings Fault Diagnosis
Fault diagnosis methods based on deep learning have progressed greatly in recent years. However, the limited training data and complex work conditions still restrict the application of these intelligent methods. This paper proposes an intelligent bearing fault diagnosis method, i.e., Siamese Vision...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/13/10/1656 |
| _version_ | 1797471210646274048 |
|---|---|
| author | Qiuchen He Shaobo Li Qiang Bai Ansi Zhang Jing Yang Mingming Shen |
| author_facet | Qiuchen He Shaobo Li Qiang Bai Ansi Zhang Jing Yang Mingming Shen |
| author_sort | Qiuchen He |
| collection | DOAJ |
| description | Fault diagnosis methods based on deep learning have progressed greatly in recent years. However, the limited training data and complex work conditions still restrict the application of these intelligent methods. This paper proposes an intelligent bearing fault diagnosis method, i.e., Siamese Vision Transformer, suiting limited training data and complex work conditions. The Siamese Vision Transformer, combining Siamese network and Vision Transformer, is designed to efficiently extract the feature vectors of input samples in high-level space and complete the classification of the fault. In addition, a new loss function combining the Kullback-Liebler divergence both directions is proposed to improve the performance of the proposed model. Furthermore, a new training strategy termed random mask is designed to enhance input data diversity. A comparative test is conducted on the Case Western Reserve University bearing dataset and Paderborn dataset and our method achieves reasonably high accuracy with limited data and satisfactory generation capability for cross-domain tasks. |
| first_indexed | 2024-03-09T19:45:57Z |
| format | Article |
| id | doaj.art-057609b20e924c75b6c2c4836e4130b0 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-09T19:45:57Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-057609b20e924c75b6c2c4836e4130b02023-11-24T01:22:16ZengMDPI AGMicromachines2072-666X2022-09-011310165610.3390/mi13101656A Siamese Vision Transformer for Bearings Fault DiagnosisQiuchen He0Shaobo Li1Qiang Bai2Ansi Zhang3Jing Yang4Mingming Shen5School of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaFault diagnosis methods based on deep learning have progressed greatly in recent years. However, the limited training data and complex work conditions still restrict the application of these intelligent methods. This paper proposes an intelligent bearing fault diagnosis method, i.e., Siamese Vision Transformer, suiting limited training data and complex work conditions. The Siamese Vision Transformer, combining Siamese network and Vision Transformer, is designed to efficiently extract the feature vectors of input samples in high-level space and complete the classification of the fault. In addition, a new loss function combining the Kullback-Liebler divergence both directions is proposed to improve the performance of the proposed model. Furthermore, a new training strategy termed random mask is designed to enhance input data diversity. A comparative test is conducted on the Case Western Reserve University bearing dataset and Paderborn dataset and our method achieves reasonably high accuracy with limited data and satisfactory generation capability for cross-domain tasks.https://www.mdpi.com/2072-666X/13/10/1656intelligent fault diagnosisvision transformerSiamese networklimited datadomain generation |
| spellingShingle | Qiuchen He Shaobo Li Qiang Bai Ansi Zhang Jing Yang Mingming Shen A Siamese Vision Transformer for Bearings Fault Diagnosis Micromachines intelligent fault diagnosis vision transformer Siamese network limited data domain generation |
| title | A Siamese Vision Transformer for Bearings Fault Diagnosis |
| title_full | A Siamese Vision Transformer for Bearings Fault Diagnosis |
| title_fullStr | A Siamese Vision Transformer for Bearings Fault Diagnosis |
| title_full_unstemmed | A Siamese Vision Transformer for Bearings Fault Diagnosis |
| title_short | A Siamese Vision Transformer for Bearings Fault Diagnosis |
| title_sort | siamese vision transformer for bearings fault diagnosis |
| topic | intelligent fault diagnosis vision transformer Siamese network limited data domain generation |
| url | https://www.mdpi.com/2072-666X/13/10/1656 |
| work_keys_str_mv | AT qiuchenhe asiamesevisiontransformerforbearingsfaultdiagnosis AT shaoboli asiamesevisiontransformerforbearingsfaultdiagnosis AT qiangbai asiamesevisiontransformerforbearingsfaultdiagnosis AT ansizhang asiamesevisiontransformerforbearingsfaultdiagnosis AT jingyang asiamesevisiontransformerforbearingsfaultdiagnosis AT mingmingshen asiamesevisiontransformerforbearingsfaultdiagnosis AT qiuchenhe siamesevisiontransformerforbearingsfaultdiagnosis AT shaoboli siamesevisiontransformerforbearingsfaultdiagnosis AT qiangbai siamesevisiontransformerforbearingsfaultdiagnosis AT ansizhang siamesevisiontransformerforbearingsfaultdiagnosis AT jingyang siamesevisiontransformerforbearingsfaultdiagnosis AT mingmingshen siamesevisiontransformerforbearingsfaultdiagnosis |