Surface defect detection algorithm of thrust ball bearing based on improved YOLOv5

被引：1
|
作者：
Yuan T.-L. [1 ]
Yuan J.-L. [1 ]
Zhu Y.-J. [2 ]
Zheng H.-C. [1 ]
机构：
[1] College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou
[2] College of Mechanical Engineering, Zhejiang University of Science and Technology, Hangzhou
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2022年 / 56卷 / 12期
关键词：
attention mechanism; deep learning; surface defect detection; thrust ball bearing; Transformer; YOLOV5;
D O I：
10.3785/j.issn.1008-973X.2022.12.004
中图分类号：
学科分类号：
摘要：
An automatic extraction detection area preprocessing and a multi-head self-attention mechanism module in the improved Transformer were proposed, in order to improve the accuracy and recall rate of the surface defect detection of thrust ball bearings, and enhance the anti-interference ability of the model. The proposed module was introduced into the feature network ignoring irrelevant noise information and focusing on the key information, and the extraction ability of small and medium-sized surface defects was improved. Instance normalization was used instead of Batch normalization to improve the convergence speed and detection accuracy during model training. Results show that in the thrust ball bearing surface defect detection dataset, the accuracy rate of the improved YOLOv5 model reaches 87.0%, the recall rate reaches 83.0%, the average precision reaches 86.1%, and the average detection time per image was 14.96 ms. Compared with the YOLOv5s model, the accuracy of the improved model is increased by 1.5%, the recall rate is increased by 7.3%, and the average precision is increased by 7.9%. Compared with the original model, the improved YOLOv5 model has better defect positioning ability and higher accuracy, and can reduce interference of foreign objects in the detection process on detection results. A detection speed of the improved YOLOv5 model can meet the requirements of industrial mass detection. © 2022 Zhejiang University. All rights reserved.
引用
下载
收藏
页码：2349 / 2357
页数：8
相关论文
共 33 条
  • [1] LIU Qiao-fang, YAN Feng, Current situation and development trend of Chinese bearing manufacturing technology [J], Bearing, 6, pp. 42-45, (2005)
  • [2] ZOU Y, DU D, CHANG B, Et al., Automatic weld defect detection method based on Kalman filtering for real-time radiographic inspection of spiral pipe [J], NDT&E International, 72, pp. 1-9, (2015)
  • [3] BEARD M D, LOWE M J S., Non-destructive testing of rock bolts using guided ultrasonic waves [J], International Journal of Rock Mechanics and Mining Sciences, 40, 4, pp. 527-536, (2003)
  • [4] TITMAN D J., Applications of thermography in non-destructive testing of structures [J], NDT&E International, 34, 2, pp. 149-154, (2001)
  • [5] LU Q Y, WONG C H., Applications of non-destructive testing techniques for post-process control of additively manufactured parts [J], Virtual and Physical Prototyping, 12, 4, pp. 301-321, (2017)
  • [6] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation [C], 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [7] HE K, ZHANG X, REN S, Et al., Spatial pyramid pooling in deep convolutional networks for visual recognition [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 9, pp. 1904-1916, (2015)
  • [8] GIRSHICK R., Fast R-CNN [J], 2015 IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [9] REN S, HE K, GIRSHICK R, Et al., Faster R-CNN: towards real-time object detection with region proposal networks [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [10] DAI J, LI Y, HE K, Et al., R-FCN: object detection via region-based fully convolutional networks [C], Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 379-387, (2016)
1234