Detection of Welding Defects Tracked by YOLOv4 Algorithm
Source abstract
Abstract
The recall rate of the original YOLOv4 model for detecting internal defects in aluminum alloy welds is relatively low. To address this issue, this paper introduces an enhanced model, YOLOv4-cs1. The improvements include optimizing the stacking method of residual blocks, modifying the activation functions for different convolutional layers, and eliminating the downsampling layer in the PANet (Pyramid Attention Network) to preserve edge information. Building on these enhancements, the YOLOv4-cs2 model further incorporates an improved Spatial Pyramid Pooling (SPP) module after the third and fourth residual blocks. The experimental results demonstrate that the recall rates for pore and slag inclusion detection using the YOLOv4-cs1 and YOLOv4-cs2 models increased by 28.9% and 16.6%, and 45% and 25.2%, respectively, compared to the original YOLOv4 model. Additionally, the mAP values for the two models are 85.79% and 87.5%, representing increases of 0.98% and 2.69%, respectively, over the original YOLOv4 model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai 201209, China
Funding
National Natural Science Foundation of China
References (25)
Show source-provided references
1. Approaches for improvement of the X-ray image defect detection of automobile casting aluminum parts based on deep learning10.1016/j.ndteint.2019.102144 ↗
2. A survey: Object detection methods from CNN to transformer10.1007/s11042-022-13801-3 ↗
3. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
4. Girshick, R. (2015). Fast R-CNN. arXiv.10.1109/ICCV.2015.169 ↗
5. Ren, S. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. arXiv.
6. Zhou, H.-Y., Gao, B.-B., and Wu, J. (2017, January 22–29). Adaptive feeding: Achieving fast and accurate detections by adaptively combining object detectors. Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.379 ↗
7. A review of yolo algorithm developments10.1016/j.procs.2022.01.135 ↗
8. Ross, T.-Y., and Dollár, G. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy.
9. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016). SSD: Single shot multibox detector. Computer Vision–ECCV 2016: 14th European Conference, Springer. Part I.10.1007/978-3-319-46448-0_2 ↗
10. Yolo-mamba: Object detection method for infrared aerial images10.1007/s11760-024-03507-4 ↗
11. Pedestrian detection using retinanet with multi-branch structure and double pooling attention mechanism10.1007/s11042-023-15862-4 ↗
12. Biffi, L.J., Mitishita, E., Liesenberg, V., dos Santos, A.A., Gonçalves, D.N., Estrabis, N.V., Silva, J.d.A., Osco, L.P., Ramos, A.P.M., and Centeno, J.A.S. (2020). Atss deep learning-based approach to detect apple fruits. Remote Sens., 13.10.3390/rs13010054 ↗
13. Weld defect detection from imbalanced radiographic images based on contrast enhancement conditional generative adversarial network and transfer learning10.1109/JSEN.2021.3059860 ↗
14. Deep learning-based weld defect classification using vgg16 transfer learning adaptive fine-tuning10.1007/s12008-023-01327-3 ↗
15. Defects detection in weld joints based on visual attention and deep learning10.1016/j.ndteint.2022.102764 ↗
16. Lf-yolo: A lighter and faster yolo for weld defect detection of X-ray image10.1109/JSEN.2023.3247006 ↗
17. Pan, K., Hu, H., and Gu, P. (2023). Wd-yolo: A more accurate yolo for defect detection in weld x-ray images. Sensors, 23.10.3390/s23218677 ↗
18. A pixel-level deep segmentation network for automatic defect detection10.1016/j.eswa.2022.119388 ↗
19. An efficient anchor-free defect detector with dynamic receptive field and task alignment10.1109/TII.2024.3371982 ↗
20. STMA-net: A spatial transformation-based multi-scale attention network for complex defect detection with X-ray images10.1109/TIM.2024.3376014 ↗
21. Weld Defect Detection based on Improved Deep Learning
22. Real-time railroad track components inspection based on the improved YOLOv4 framework10.1016/j.autcon.2021.103596 ↗
23. Mi, J., Wen, X., Sun, C., Lu, Z., and Jing, W. (2019, January 11–13). Energy-efficient and Low Package Loss Clustering in UAV-assisted WSN using Kmeans++ and Fuzzy Logic. Proceedings of the 2019 IEEE/CIC International Conference on Communications Workshops in China, ICCC Workshops 2019, Changchun, China.10.1109/ICCChinaW.2019.8849956 ↗
24. Prediction of hydraulics performance in drain envelopes using Kmeans based multivariate adaptive regression spline10.1016/j.asoc.2020.107008 ↗
25. An multi-scale learning network with depthwise separable convolutions10.1186/s41074-018-0047-6 ↗