Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5
A pretty crucial step in the manufacturing of gears is the defect detection on gear surfaces. An algorithmic detection model called BN-YOLOv5 which is based on an improved YOLOv5 is proposed in order to increase the accuracy of gear surface defect detection. Firstly, the technique strengthens the ne...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2024-05-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.05.020 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841546938555564032 |
|---|---|
| author | Zhao Xiaohui Zhang Zhijie Hu Sheng Huan Kaixuan Liu Lei Pu Junping |
| author_facet | Zhao Xiaohui Zhang Zhijie Hu Sheng Huan Kaixuan Liu Lei Pu Junping |
| author_sort | Zhao Xiaohui |
| collection | DOAJ |
| description | A pretty crucial step in the manufacturing of gears is the defect detection on gear surfaces. An algorithmic detection model called BN-YOLOv5 which is based on an improved YOLOv5 is proposed in order to increase the accuracy of gear surface defect detection. Firstly, the technique strengthens the network's capacity to extract various features by embedding the weighted bidirectional feature pyramid network structure into the neck network structure. Secondly, a compact focus mechanism module, normalization-based attention module (NAM) is presented to its weighted bidirectional feature pyramid network structure which can more rapidly and efficiently fuse the feature information of higher and lower layers. Finally, the depth separable convolution module is used to replace every convolutional layer in the network structure, thereby lightening the network model. The experimental findings demonstrate that the enhanced algorithm model can achieve an average accuracy of 98.5%, a detection speed of 66 frames per second, and a modelling size of 9.69 MB, which effectively reduces the memory footprint of the model, and enables the task of real-time inspection of gear surface defects on small mobile devices. |
| format | Article |
| id | doaj-art-465ce18a62d04651be36aec3faa7d053 |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2024-05-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-465ce18a62d04651be36aec3faa7d0532025-01-10T15:00:34ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392024-05-014814515159003924Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5Zhao XiaohuiZhang ZhijieHu ShengHuan KaixuanLiu LeiPu JunpingA pretty crucial step in the manufacturing of gears is the defect detection on gear surfaces. An algorithmic detection model called BN-YOLOv5 which is based on an improved YOLOv5 is proposed in order to increase the accuracy of gear surface defect detection. Firstly, the technique strengthens the network's capacity to extract various features by embedding the weighted bidirectional feature pyramid network structure into the neck network structure. Secondly, a compact focus mechanism module, normalization-based attention module (NAM) is presented to its weighted bidirectional feature pyramid network structure which can more rapidly and efficiently fuse the feature information of higher and lower layers. Finally, the depth separable convolution module is used to replace every convolutional layer in the network structure, thereby lightening the network model. The experimental findings demonstrate that the enhanced algorithm model can achieve an average accuracy of 98.5%, a detection speed of 66 frames per second, and a modelling size of 9.69 MB, which effectively reduces the memory footprint of the model, and enables the task of real-time inspection of gear surface defects on small mobile devices.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.05.020Gear surfaceDefect detectionYOLOv5LightweightNAM attention mechanism |
| spellingShingle | Zhao Xiaohui Zhang Zhijie Hu Sheng Huan Kaixuan Liu Lei Pu Junping Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 Jixie chuandong Gear surface Defect detection YOLOv5 Lightweight NAM attention mechanism |
| title | Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 |
| title_full | Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 |
| title_fullStr | Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 |
| title_full_unstemmed | Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 |
| title_short | Research on the Lightweight Gear Surface Defect Detection Algorithm Based on BN-YOLOv5 |
| title_sort | research on the lightweight gear surface defect detection algorithm based on bn yolov5 |
| topic | Gear surface Defect detection YOLOv5 Lightweight NAM attention mechanism |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.05.020 |
| work_keys_str_mv | AT zhaoxiaohui researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 AT zhangzhijie researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 AT husheng researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 AT huankaixuan researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 AT liulei researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 AT pujunping researchonthelightweightgearsurfacedefectdetectionalgorithmbasedonbnyolov5 |