Bearing fault diagnosis based on cross image multi-attention mechanism
Abstract Bearings are crucial components of rotating machinery, and fault diagnosis is essential for ensuring the safe operation of mechanical systems. Neural networks, commonly used in bearing fault diagnosis, are effective in extracting deep features from fault signals but often fail to emphasize...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-07562-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769324721471488 |
|---|---|
| author | Yupeng Liu Weinan Zheng Ying Du Yuehui Wang Jian Jin Miao Yu |
| author_facet | Yupeng Liu Weinan Zheng Ying Du Yuehui Wang Jian Jin Miao Yu |
| author_sort | Yupeng Liu |
| collection | DOAJ |
| description | Abstract Bearings are crucial components of rotating machinery, and fault diagnosis is essential for ensuring the safe operation of mechanical systems. Neural networks, commonly used in bearing fault diagnosis, are effective in extracting deep features from fault signals but often fail to emphasize critical information. We propose a fault diagnosis method that integrates a cross-image multi-attention mechanism with a residual neural network. The collected vibration signals are first preprocessed using VMD-GAF and then fed into the network for fault detection. The results demonstrate that the CIMAM-ResNet18 model significantly enhances the robustness of signal processing, achieving an accuracy of 98.00% when tested on the experimental platform. |
| format | Article |
| id | doaj-art-7d02c12855864cdab5bcbe72340afa39 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7d02c12855864cdab5bcbe72340afa392025-08-20T03:03:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111010.1038/s41598-025-07562-wBearing fault diagnosis based on cross image multi-attention mechanismYupeng Liu0Weinan Zheng1Ying Du2Yuehui Wang3Jian Jin4Miao Yu5School of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologySchool of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologySchool of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologySchool of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologySchool of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologySchool of Electrical and Mechanical Engineering, Jilin University of Architecture and TechnologyAbstract Bearings are crucial components of rotating machinery, and fault diagnosis is essential for ensuring the safe operation of mechanical systems. Neural networks, commonly used in bearing fault diagnosis, are effective in extracting deep features from fault signals but often fail to emphasize critical information. We propose a fault diagnosis method that integrates a cross-image multi-attention mechanism with a residual neural network. The collected vibration signals are first preprocessed using VMD-GAF and then fed into the network for fault detection. The results demonstrate that the CIMAM-ResNet18 model significantly enhances the robustness of signal processing, achieving an accuracy of 98.00% when tested on the experimental platform.https://doi.org/10.1038/s41598-025-07562-wBearing fault diagnosisMulti-attention mechanismCIMAM-ResNet18 |
| spellingShingle | Yupeng Liu Weinan Zheng Ying Du Yuehui Wang Jian Jin Miao Yu Bearing fault diagnosis based on cross image multi-attention mechanism Scientific Reports Bearing fault diagnosis Multi-attention mechanism CIMAM-ResNet18 |
| title | Bearing fault diagnosis based on cross image multi-attention mechanism |
| title_full | Bearing fault diagnosis based on cross image multi-attention mechanism |
| title_fullStr | Bearing fault diagnosis based on cross image multi-attention mechanism |
| title_full_unstemmed | Bearing fault diagnosis based on cross image multi-attention mechanism |
| title_short | Bearing fault diagnosis based on cross image multi-attention mechanism |
| title_sort | bearing fault diagnosis based on cross image multi attention mechanism |
| topic | Bearing fault diagnosis Multi-attention mechanism CIMAM-ResNet18 |
| url | https://doi.org/10.1038/s41598-025-07562-w |
| work_keys_str_mv | AT yupengliu bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism AT weinanzheng bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism AT yingdu bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism AT yuehuiwang bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism AT jianjin bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism AT miaoyu bearingfaultdiagnosisbasedoncrossimagemultiattentionmechanism |