Workpiece surface defect detection based on YOLOv11 and edge computing.
The rapid development of modern industry has significantly raised the demand for workpieces. To ensure the quality of workpieces, workpiece surface defect detection has become an indispensable part of industrial production. Most workpiece surface defect detection technologies rely on cloud computing...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0327546 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849320776688205824 |
|---|---|
| author | Zishuo Wang Tao Ding Shuning Liang Hongwei Cui Xingquan Gao |
| author_facet | Zishuo Wang Tao Ding Shuning Liang Hongwei Cui Xingquan Gao |
| author_sort | Zishuo Wang |
| collection | DOAJ |
| description | The rapid development of modern industry has significantly raised the demand for workpieces. To ensure the quality of workpieces, workpiece surface defect detection has become an indispensable part of industrial production. Most workpiece surface defect detection technologies rely on cloud computing. However, transmitting large volumes of data via wireless networks places substantial computational burdens on cloud servers, significantly reducing defect detection speed. Therefore, to enable efficient and precise detection, this paper proposes a workpiece surface defect detection method based on YOLOv11 and edge computing. First, the NEU-DET dataset was expanded using random flipping, cropping, and the self-attention generative adversarial network (SA-GAN). Then, the accuracy indicators of the YOLOv7-YOLOv11 models were compared on NEU-DET and validated on the Tianchi aluminium profile surface defect dataset. Finally, the cloud-based YOLOv11 model, which achieved the highest accuracy, was converted to the edge-based YOLOv11-RKNN model and deployed on the RK3568 edge device to improve the detection speed. Results indicate that YOLOv11 with SA-GAN achieved mAP@0.5 improvements of 7.7%, 3.1%, 5.9%, and 7.0% over YOLOv7, YOLOv8, YOLOv9, and YOLOv10, respectively, on the NEU-DET dataset. Moreover, YOLOv11 with SA-GAN achieved an 87.0% mAP@0.5 on the Tianchi aluminium profile surface defect dataset, outperforming the other models again. This verifies the generalisability of the YOLOv11 model. Additionally, quantising and deploying YOLOv11 on the edge device reduced its size from 10,156 kB to 4,194 kB and reduced its single-image detection time from 52.1ms to 33.6ms, which represents a significant efficiency enhancement. |
| format | Article |
| id | doaj-art-d5bd3270b89d4abeac5fb7d50e69b00c |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-d5bd3270b89d4abeac5fb7d50e69b00c2025-08-20T03:49:59ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032754610.1371/journal.pone.0327546Workpiece surface defect detection based on YOLOv11 and edge computing.Zishuo WangTao DingShuning LiangHongwei CuiXingquan GaoThe rapid development of modern industry has significantly raised the demand for workpieces. To ensure the quality of workpieces, workpiece surface defect detection has become an indispensable part of industrial production. Most workpiece surface defect detection technologies rely on cloud computing. However, transmitting large volumes of data via wireless networks places substantial computational burdens on cloud servers, significantly reducing defect detection speed. Therefore, to enable efficient and precise detection, this paper proposes a workpiece surface defect detection method based on YOLOv11 and edge computing. First, the NEU-DET dataset was expanded using random flipping, cropping, and the self-attention generative adversarial network (SA-GAN). Then, the accuracy indicators of the YOLOv7-YOLOv11 models were compared on NEU-DET and validated on the Tianchi aluminium profile surface defect dataset. Finally, the cloud-based YOLOv11 model, which achieved the highest accuracy, was converted to the edge-based YOLOv11-RKNN model and deployed on the RK3568 edge device to improve the detection speed. Results indicate that YOLOv11 with SA-GAN achieved mAP@0.5 improvements of 7.7%, 3.1%, 5.9%, and 7.0% over YOLOv7, YOLOv8, YOLOv9, and YOLOv10, respectively, on the NEU-DET dataset. Moreover, YOLOv11 with SA-GAN achieved an 87.0% mAP@0.5 on the Tianchi aluminium profile surface defect dataset, outperforming the other models again. This verifies the generalisability of the YOLOv11 model. Additionally, quantising and deploying YOLOv11 on the edge device reduced its size from 10,156 kB to 4,194 kB and reduced its single-image detection time from 52.1ms to 33.6ms, which represents a significant efficiency enhancement.https://doi.org/10.1371/journal.pone.0327546 |
| spellingShingle | Zishuo Wang Tao Ding Shuning Liang Hongwei Cui Xingquan Gao Workpiece surface defect detection based on YOLOv11 and edge computing. PLoS ONE |
| title | Workpiece surface defect detection based on YOLOv11 and edge computing. |
| title_full | Workpiece surface defect detection based on YOLOv11 and edge computing. |
| title_fullStr | Workpiece surface defect detection based on YOLOv11 and edge computing. |
| title_full_unstemmed | Workpiece surface defect detection based on YOLOv11 and edge computing. |
| title_short | Workpiece surface defect detection based on YOLOv11 and edge computing. |
| title_sort | workpiece surface defect detection based on yolov11 and edge computing |
| url | https://doi.org/10.1371/journal.pone.0327546 |
| work_keys_str_mv | AT zishuowang workpiecesurfacedefectdetectionbasedonyolov11andedgecomputing AT taoding workpiecesurfacedefectdetectionbasedonyolov11andedgecomputing AT shuningliang workpiecesurfacedefectdetectionbasedonyolov11andedgecomputing AT hongweicui workpiecesurfacedefectdetectionbasedonyolov11andedgecomputing AT xingquangao workpiecesurfacedefectdetectionbasedonyolov11andedgecomputing |