Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)

<Previous Article In Volume
Next Article In Volume>

Development of Automated Welding Defect Detection Based on YOLO Algorithm

Authors
Junwei Tan1, Helin Xu2, *, Xintong Zhang3
1School of Education, Beijing Institute of Technology, Beijing, China
2HDU-ITMO Joint Institute, Hangzhou Dianzi University, Zhejiang, China
3Department of Information Science and Engineering, Ocean University of China, Shandong, China
*Corresponding author. Email: 23320411@hdu.edu.cn
Corresponding Author
Helin Xu
Available Online 31 August 2025.
DOI
10.2991/978-94-6463-821-9_100How to use a DOI?
Keywords
Machine vision; deep learning; YOLO; Automated welding; defect detection
Abstract

The application of deep learning algorithms to welding defect detection has advanced rapidly in recent years within domestic and international research communities. This paper reviews the developmental trajectory of deep learning technologies and the evolutionary improvements of the You Only Look Once (YOLO) algorithm from versions v1 to v11. Focusing on the application of YOLO in welding defect detection, it provides a systematic exposition of architectural enhancements in the YOLOv3 to YOLOv8 series, particularly in five key aspects: noise robustness optimization, real-time performance optimization, adaptive feature selection, feature fusion, and lightweight design, while critically analyzing their innovative contributions. A comprehensive comparative analysis of these models reveals that, despite continuous efforts by global laboratories to develop novel YOLO variants for welding processes, the generalization capabilities of existing technologies under complex operational conditions still require further enhancement. Building on this conclusion, the paper prospects the application potential of multi-scale analysis and few-shot learning in welding defect detection and outlines future research directions in this field.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
Series
Advances in Engineering Research
Publication Date
31 August 2025
ISBN
978-94-6463-821-9
ISSN
2352-5401
DOI
10.2991/978-94-6463-821-9_100How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Junwei Tan
AU  - Helin Xu
AU  - Xintong Zhang
PY  - 2025
DA  - 2025/08/31
TI  - Development of Automated Welding Defect Detection Based on YOLO Algorithm
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 1029
EP  - 1044
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_100
DO  - 10.2991/978-94-6463-821-9_100
ID  - Tan2025
ER  -