NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm
Electronics · 17.07.2025 · 14 (14) · 2859
DOI: 10.3390/electronics14142859 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 17.07.2025. Verfasst von Bingyi Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Province Natural Science Foundation, Changzhou Sci&Tech Program, Open Research Fund of Hubei Technology Innovation Center for Smart Hydropower.
Abstract (Originalsprache)
Steel surface defect detection is a crucial step in ensuring industrial production quality. However, due to significant variations in scale and irregular geometric morphology of steel surface defects, existing detection algorithms show notable deficiencies in multi-scale feature representation and cross-layer multi-scale feature fusion efficiency. To address these challenges, this paper proposes an improved real-time steel surface defect detection model, NGD-YOLO, based on YOLOv5s, which achieves fast and high-precision defect detection under relatively low hardware conditions. Firstly, a lightweight and efficient Normalization-based Attention Module (NAM) is integrated into the C3 module to construct the C3NAM, enhancing multi-scale feature representation capabilities. Secondly, an efficient Gather–Distribute (GD) mechanism is introduced into the feature fusion component to build the GD-NAM network, thereby effectively reducing information loss during cross-layer multi-scale information fusion and adding a small target detection layer to enhance the detection performance of small defects. Finally, to mitigate the parameter increase caused by the GD-NAM network, a lightweight convolution module, DCConv, that integrates Efficient Channel Attention (ECA), is proposed and combined with the C3 module to construct the lightweight C3DC module. This approach improves detection speed and accuracy while reducing model parameters. Experimental results on the public NEU-DET dataset show that the proposed NGD-YOLO model achieves a detection accuracy of 79.2%, representing a 4.6% mAP improvement over the baseline YOLOv5s network with less than a quarter increase in parameters, and reaches 108.6 FPS, meeting the real-time monitoring requirements in industrial production environments.
Förderung
- Jiangsu Province Natural Science Foundation
- Changzhou Sci&Tech Program
- Open Research Fund of Hubei Technology Innovation Center for Smart Hydropower
Zitieren
APA
Li, B., Xiao, A., Hu, X., Zhu, S., Wan, G., Qi, K., & Shi, P. (2025). NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm. Electronics, 14(14), 2859. https://doi.org/10.3390/electronics14142859
Vancouver
Li B, Xiao A, Hu X, Zhu S, Wan G, Qi K, et al. NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm. Electronics. 2025;14(14):2859. doi:10.3390/electronics14142859
BibTeX
@article{Li2025,
author = {Li, Bingyi and Xiao, Andong and Hu, Xing and Zhu, Sisi and Wan, Gang and Qi, Kunlun and Shi, Pengfei},
title = {NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm},
journal = {Electronics},
year = {2025},
volume = {14},
number = {14},
pages = {2859},
doi = {10.3390/electronics14142859}
}
EUVIMED