EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model

Bangzhi Xiao iD, Yadong Yang, Yinshui He iD, Guohong Ma

Materials · 17.03.2026 · 19 (6) · 1178

DOI: 10.3390/ma19061178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 17.03.2026. Verfasst von Bangzhi Xiao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Advanced Manufacturing, Nanchang University, Nanchang 330031, China. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Shop-floor weld inspection may appear to be a solved problem until a camera is deployed near a galvanized-sheet MIG welding line. The seam reflects light, the texture changes from frame to frame, and the defects of interest are often small and visually subtle. Additionally, the hardware near the line is rarely a data-center GPU. With those constraints in mind, this paper presents YOLO-MIG, a compact detector built on YOLOv10n for weld-seam inspection in practical production conditions. We make three focused changes to the baseline: a C2f-EMSCP backbone block to better preserve weak defect cues with modest parameter growth, a BiFPN neck to keep small-target information alive during feature fusion, and a C2fCIB head to clean up predictions that otherwise get distracted by seam edges and illumination artifacts. On a workshop-collected dataset containing 326 original images, with the training subset expanded through augmentation to 2608 labeled samples in total, YOLO-MIG achieves 98.4% mAP@0.5 and 56.29% mAP@0.5:0.95 on the test set while remaining lightweight (1.83 M parameters, 3.87 MB FP16 weights). Compared with YOLOv10n, the proposed model improves mAP@0.5 by 9.36 points and mAP@0.5:0.95 by 4.89 points, while reducing parameters, GFLOPs, and model size by 43.4%, 19.9%, and 29.9%, respectively. The results suggest that YOLO-MIG is not only accurate but also realistic to deploy at the edge for intelligent weld quality control.

Schlagwörter

Stichwörter der Autor:innen

YOLOv10lightweight neural networkweld porosity detection

Autor:innen und Institutionen

  • School of Advanced Manufacturing, Nanchang University, Nanchang 330031, China.
  • Key Laboratory of Light Alloy of Jiangxi Province, Nanchang University, Nanchang 330031, China.
  • School of Resources Environmental and Chemical Engineering, Nanchang University, 999 Xuefu Avenue, Nanchang 330031, China.

ORCID-Profile: Bangzhi Xiao, Yinshui He

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xiao, B., Yang, Y., He, Y., & Ma, G. (2026). Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model. Materials, 19(6), 1178. https://doi.org/10.3390/ma19061178

Vancouver

Xiao B, Yang Y, He Y, Ma G. Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model. Materials. 2026;19(6):1178. doi:10.3390/ma19061178

BibTeX
@article{Xiao2026,
  author = {Xiao, Bangzhi and Yang, Yadong and He, Yinshui and Ma, Guohong},
  title = {Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {1178},
  doi = {10.3390/ma19061178}
}
Kostenlos starten →