TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion
Abstract The intelligent identification of wear particles in ferrography is a critical bottleneck that hampers the development and widespread adoption of ferrography technology. To address challenges such as false detection, missed detection of small wear particles, difficulty in distinguishing over...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82961-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850075728278716416 |
|---|---|
| author | Lei He Haijun Wei Cunxun Sun |
| author_facet | Lei He Haijun Wei Cunxun Sun |
| author_sort | Lei He |
| collection | DOAJ |
| description | Abstract The intelligent identification of wear particles in ferrography is a critical bottleneck that hampers the development and widespread adoption of ferrography technology. To address challenges such as false detection, missed detection of small wear particles, difficulty in distinguishing overlapping and similar abrasions, and handling complex image backgrounds, this paper proposes an algorithm called TCBGY-Net for detecting wear particles in ferrography images. The proposed TCBGY-Net uses YOLOv5s as the backbone network, which is enhanced with several advanced modules to improve detection performance. Firstly, we integrate a Transformer module based on the self-attention mechanism with the C3 module at the end of the backbone network to form a C3TR module. This integration enhances the global feature extraction capability of the backbone network and improves its ability to detect small target wear particles. Secondly, we introduce the convolutional block attention module (CBAM) into the neck network to enhance salience for detecting wear particles while suppressing irrelevant information interference. Furthermore, multi-scale feature maps extracted by the backbone network are fed into the bidirectional feature pyramid network (BiFPN) for feature fusion to enhance the model’s ability to detect wear particle feature maps at different scales. Lastly, Ghost modules are introduced into both the backbone network and the neck network to reduce their complexity and improve detection speed. Experimental results demonstrate that TCBGY-Net achieves outstanding precision in detecting wear particles against complex backgrounds, with a mAP@0.5 value of 98.3%, which is a 10.2% improvement over YOLOv5s. In addition, we conducted comprehensive ablation experiments, to validate the contribution of each module and the robustness of our model. TCBGY-Net also outperforms most current mainstream algorithms in terms of detection speed, with up to 89.2 FPS capability, thus providing favorable conditions for subsequent real-time online monitoring of changes in wear particles and fault diagnosis in ship power systems. |
| format | Article |
| id | doaj-art-fe828dc3c1ad46fbb130a465b68b5bac |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-fe828dc3c1ad46fbb130a465b68b5bac2025-08-20T02:46:13ZengNature PortfolioScientific Reports2045-23222024-12-0114112210.1038/s41598-024-82961-zTCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusionLei He0Haijun Wei1Cunxun Sun2Merchant Marine College, Shanghai Maritime UniversityMerchant Marine College, Shanghai Maritime UniversityMerchant Marine College, Shanghai Maritime UniversityAbstract The intelligent identification of wear particles in ferrography is a critical bottleneck that hampers the development and widespread adoption of ferrography technology. To address challenges such as false detection, missed detection of small wear particles, difficulty in distinguishing overlapping and similar abrasions, and handling complex image backgrounds, this paper proposes an algorithm called TCBGY-Net for detecting wear particles in ferrography images. The proposed TCBGY-Net uses YOLOv5s as the backbone network, which is enhanced with several advanced modules to improve detection performance. Firstly, we integrate a Transformer module based on the self-attention mechanism with the C3 module at the end of the backbone network to form a C3TR module. This integration enhances the global feature extraction capability of the backbone network and improves its ability to detect small target wear particles. Secondly, we introduce the convolutional block attention module (CBAM) into the neck network to enhance salience for detecting wear particles while suppressing irrelevant information interference. Furthermore, multi-scale feature maps extracted by the backbone network are fed into the bidirectional feature pyramid network (BiFPN) for feature fusion to enhance the model’s ability to detect wear particle feature maps at different scales. Lastly, Ghost modules are introduced into both the backbone network and the neck network to reduce their complexity and improve detection speed. Experimental results demonstrate that TCBGY-Net achieves outstanding precision in detecting wear particles against complex backgrounds, with a mAP@0.5 value of 98.3%, which is a 10.2% improvement over YOLOv5s. In addition, we conducted comprehensive ablation experiments, to validate the contribution of each module and the robustness of our model. TCBGY-Net also outperforms most current mainstream algorithms in terms of detection speed, with up to 89.2 FPS capability, thus providing favorable conditions for subsequent real-time online monitoring of changes in wear particles and fault diagnosis in ship power systems.https://doi.org/10.1038/s41598-024-82961-zFerrographyTransformerSmall object detectionBiFPNModel lightweigh |
| spellingShingle | Lei He Haijun Wei Cunxun Sun TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion Scientific Reports Ferrography Transformer Small object detection BiFPN Model lightweigh |
| title | TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| title_full | TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| title_fullStr | TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| title_full_unstemmed | TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| title_short | TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| title_sort | tcbgy net for enhanced wear particle detection in ferrography using self attention and multi scale fusion |
| topic | Ferrography Transformer Small object detection BiFPN Model lightweigh |
| url | https://doi.org/10.1038/s41598-024-82961-z |
| work_keys_str_mv | AT leihe tcbgynetforenhancedwearparticledetectioninferrographyusingselfattentionandmultiscalefusion AT haijunwei tcbgynetforenhancedwearparticledetectioninferrographyusingselfattentionandmultiscalefusion AT cunxunsun tcbgynetforenhancedwearparticledetectioninferrographyusingselfattentionandmultiscalefusion |