A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning
Abstract To address the insufficient generalization capability of bearing fault diagnosis models caused by scarce vibration data from high-power hydrodynamic transmission testbeds, this study proposes a diagnostic method integrating deep few-shot learning with transfer learning. First, a Siamese Wid...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-04543-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849688073641656320 |
|---|---|
| author | Dong Sun Xudong Yang Hai Yang |
| author_facet | Dong Sun Xudong Yang Hai Yang |
| author_sort | Dong Sun |
| collection | DOAJ |
| description | Abstract To address the insufficient generalization capability of bearing fault diagnosis models caused by scarce vibration data from high-power hydrodynamic transmission testbeds, this study proposes a diagnostic method integrating deep few-shot learning with transfer learning. First, a Siamese Wide Convolutional Neural Network (Siamese-WDCNN) is constructed based on public bearing datasets to extract essential features of vibration signals through few-shot contrastive learning. Second, we introduce a transfer learning strategy to address cross-condition generalization challenges. This approach adapts pre-trained model parameters from the CWRU dataset to real industrial hydrodynamic transmission data. We then fine-tune the model using limited target-domain samples to optimize performance. Experiments evaluating the generalization capability under variable operating conditions compare diagnostic performance across SVM, WDCNN, WDCNN + TL, FSL + TL, and FSL + TL + AM methods. Results demonstrate that FSL + TL achieves an accuracy of 85.30% under mixed operating conditions. Further optimization by incorporating an attention mechanism (FSL + TL + AM) elevates accuracy to 88.75%, effectively enhancing the generalization capability of the bearing fault diagnosis model. This validates the engineering practicality of the proposed method and explores a viable pathway for industrial equipment health monitoring. |
| format | Article |
| id | doaj-art-46c0da99871c46f281027f110f01fc68 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-46c0da99871c46f281027f110f01fc682025-08-20T03:22:08ZengNature PortfolioScientific Reports2045-23222025-05-0115111710.1038/s41598-025-04543-xA bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learningDong Sun0Xudong Yang1Hai Yang2School of Mechanical Engineering, Guizhou UniversitySchool of Mechanical Engineering, Guizhou UniversitySchool of Mechanical Engineering, Guizhou UniversityAbstract To address the insufficient generalization capability of bearing fault diagnosis models caused by scarce vibration data from high-power hydrodynamic transmission testbeds, this study proposes a diagnostic method integrating deep few-shot learning with transfer learning. First, a Siamese Wide Convolutional Neural Network (Siamese-WDCNN) is constructed based on public bearing datasets to extract essential features of vibration signals through few-shot contrastive learning. Second, we introduce a transfer learning strategy to address cross-condition generalization challenges. This approach adapts pre-trained model parameters from the CWRU dataset to real industrial hydrodynamic transmission data. We then fine-tune the model using limited target-domain samples to optimize performance. Experiments evaluating the generalization capability under variable operating conditions compare diagnostic performance across SVM, WDCNN, WDCNN + TL, FSL + TL, and FSL + TL + AM methods. Results demonstrate that FSL + TL achieves an accuracy of 85.30% under mixed operating conditions. Further optimization by incorporating an attention mechanism (FSL + TL + AM) elevates accuracy to 88.75%, effectively enhancing the generalization capability of the bearing fault diagnosis model. This validates the engineering practicality of the proposed method and explores a viable pathway for industrial equipment health monitoring.https://doi.org/10.1038/s41598-025-04543-xHydrodynamic transmissionBearing fault diagnosisFew-shot learningTransfer learningAttention mechanism |
| spellingShingle | Dong Sun Xudong Yang Hai Yang A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning Scientific Reports Hydrodynamic transmission Bearing fault diagnosis Few-shot learning Transfer learning Attention mechanism |
| title | A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning |
| title_full | A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning |
| title_fullStr | A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning |
| title_full_unstemmed | A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning |
| title_short | A bearing fault diagnosis method for hydrodynamic transmissions integrating few-shot learning and transfer learning |
| title_sort | bearing fault diagnosis method for hydrodynamic transmissions integrating few shot learning and transfer learning |
| topic | Hydrodynamic transmission Bearing fault diagnosis Few-shot learning Transfer learning Attention mechanism |
| url | https://doi.org/10.1038/s41598-025-04543-x |
| work_keys_str_mv | AT dongsun abearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning AT xudongyang abearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning AT haiyang abearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning AT dongsun bearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning AT xudongyang bearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning AT haiyang bearingfaultdiagnosismethodforhydrodynamictransmissionsintegratingfewshotlearningandtransferlearning |