EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MGDR-YOLO: An Efficient Multi-Backbone YOLOv11 Framework for X-Ray Weld Defect Inspection

Jiuyang Yu iD, Pan Liu, Yaonan Dai iD, Zelin Fu, Hui Zhou, Peiyan Yang iD, Xiaotao Zheng

Sensors · 25.05.2026 · 26 (11) · 3354

DOI: 10.3390/s26113354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.05.2026. Verfasst von Jiuyang Yu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Provincial Engineering Technology Research Center of Green Chemical Equipment, School of Mechanical and Electrical Engineering, Wuhan Institute…. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the detection challenges in X-ray weld seam images caused by weak contrast, slender structures, and multi-scale coexistence, we propose MGDR-YOLO, an industrially deployable detector with four coordinated designs. First, a MultiBackbone parallel heterogeneous backbone is designed to perform complementary direction–detail modeling and lightweight context modeling under a shared shallow stem, enhancing the joint representation of fine-grained features and global semantics. Second, Gated Attention Fusion Block (GAFB) is introduced to perform selective in-scale fusion via channel gating and local–global attention mechanisms, thereby suppressing channel redundancy and noise leakage induced by naive concatenation. Third, Directional Feature Convolution (DFConv) decouples standard 2D convolution into horizontal and vertical branches and fuses them using depthwise separable convolution, substantially reducing computational cost while preserving geometric alignment. Finally, Rep Shared Convolutional Detection Head (RSCD) improves detection head consistency and inference throughput through cross-scale shared convolutions and a training-to-deployment re-parameterization scheme. The experimental results show that MGDR-YOLO significantly outperforms YOLOv11n, increasing the mean average precision (mAP) from 92.9% to 95.2%. The performance gain is most pronounced for the LP class (slender and low-contrast defects), with an mAP improvement of 10.1 percentage points. Meanwhile, the proposed model achieves a 39.4% increase in frames per second (FPS) while reducing the number of parameters by 46.2%, demonstrating superior efficiency. These results indicate that MGDR-YOLO consistently improves the accuracy and robustness of X-ray weld defect detection while maintaining real-time performance, making it well suited for resource-constrained industrial online inspection scenarios.

Schlagwörter

Stichwörter der Autor:innen

X-ray weld defect detectiondirectional convolutiongated attention fusionmulti-backbone networksre-parameterized shared detection head

Autor:innen und Institutionen

  • Hubei Provincial Engineering Technology Research Center of Green Chemical Equipment, School of Mechanical and Electrical Engineering, Wuhan Institute of Technology, Wuhan 430205, China.
  • Hubei Provincial Key Laboratory of Chemical Equipment Intensification and Intrinsic Safety, School of Mechanical and Electrical Engineering, Wuhan Institute of Technology, Wuhan 430205, China.
  • Hubei Yihua Group Chemical Machinery Equipment Manufacturing and Installation Co., Ltd., No. 399, Xiaoting Street, Xiaoting District, Yichang 443007, China.

ORCID-Profile: Jiuyang Yu, Yaonan Dai, Peiyan Yang

Zitieren

APA

Yu, J., Liu, P., Dai, Y., Fu, Z., Zhou, H., Yang, P., & Zheng, X. (2026). MGDR-YOLO: An Efficient Multi-Backbone YOLOv11 Framework for X-Ray Weld Defect Inspection. Sensors, 26(11), 3354. https://doi.org/10.3390/s26113354

Vancouver

Yu J, Liu P, Dai Y, Fu Z, Zhou H, Yang P, et al. MGDR-YOLO: An Efficient Multi-Backbone YOLOv11 Framework for X-Ray Weld Defect Inspection. Sensors. 2026;26(11):3354. doi:10.3390/s26113354

BibTeX
@article{Yu2026,
  author = {Yu, Jiuyang and Liu, Pan and Dai, Yaonan and Fu, Zelin and Zhou, Hui and Yang, Peiyan and Zheng, Xiaotao},
  title = {MGDR-YOLO: An Efficient Multi-Backbone YOLOv11 Framework for X-Ray Weld Defect Inspection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3354},
  doi = {10.3390/s26113354}
}
Kostenlos starten →