Weld proximity defect detection model for steel thin plates based on EP-YOLOv7

Runmei Zhang1, Jingwei Fan2, Zihua Chen1, 3, Zhong Chen2 and Bin Yuan2

  1. School of Electronic and Information Engineering, Anhui Jianzhu University
    230000 Hefei, China
    zhangrong@ahjzu.edu.cn, czh1619@ahjzu.edu.cn
  2. School of Mechanical and Electrical Engineering, Anhui Jianzhu University
    230000 Hefei, China
    fjw3516@stu.ahjzu.edu.cn, cz1982@ahjzu.edu.cn, yuanbinwork@163.com
  3. Provincial and Ministerial Key Laboratory, Chang’an University
    710000 Xi’an, China
    czh1619@ahjzu.edu.cn

Abstract

Quality inspection of steel plate welding is critical in industrial manufacturing. However, weld proximity defects often present diverse morphologies, overlapping regions, and dense distributions, posing challenges to accurate industrial defect inspection. Therefore, we propose an industrial detector based on the EP-YOLOv7. First, an Efficient Multiscale Channel Attention (EMCA) is introduced to strengthen multi-scale feature perception and improve the model’s focus on weld proximity defects. Second, the EMCA module is integrated into the Efficient Layer Aggregation Network to enhance feature fusion and defect representation. Finally, a Partial-Bottleneck Decoupling Predictor Head (P-BD Head) is designed to significantly improve localization accuracy and reduce missed detections of small targets. Experimental evaluations on both a self-built weld proximity defect dataset and a public generalization dataset show that EP-YOLOv7 achieves mAP of 85.2%/56.2% and F1 scores of 80.3%/43.3%. Meanwhile, the model size increases by only 0.6 MB (total 37.9 MB), demonstrating that the proposed approach delivers substantial accuracy gains while maintaining lightweight computational complexity, suitable for practical industrial applications.

Key words

Weld proximity defects, YOLOv7, EMCA, P-BD Head, machine learning

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS250922007Z

Publication information

Volume 23, Issue 1 (January 2026)
Year of Publication: 2026
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Zhang, R., Fan, J., Chen, Z., Chen, Z., Yuan, B.: Weld proximity defect detection model for steel thin plates based on EP-YOLOv7. Computer Science and Information Systems, Vol. 23, No. 1, 255-276. (2026), https://doi.org/10.2298/CSIS250922007Z