EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EP-YOLO: A Printed Circuit Board Defect Detection Network Integrating Coordinate Attention and Multi-Level Gradient Flow Optimization

Xiangsuo Fan iD, Can Yang iD, Ling Yu

Sensors · 14.05.2026 · 26 (10) · 3106

DOI: 10.3390/s26103106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.05.2026. Verfasst von Xiangsuo Fan und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Guangxi Key Research and Development Program, the research project funded by Natural Science Foundation of Guangxi Zhuang Autonomous Region, Natural Science Foundation of Guangxi Zhuang Autonomous Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The dependence of electronic products on printed circuit boards (PCBs) is increasing. In recent years, PCB defect detection technology has achieved considerable results, but the defect targets are small, the background is complex, and there are many integrated components, which poses great challenges to product quality control. Therefore, this paper proposes a printed circuit board defect detection network that integrates coordinate attention and multi-level gradient flow optimization, called EP-YOLO, to improve the detection accuracy of printed circuit board defects. Firstly, this paper improves the model’s ability to capture small target details by reconstructing the detection head of the small target. Based on this, a Shallow Context Feature Extraction (SCFE) network is designed to fuse shallow features with multi-scale features, effectively preventing the loss of shallow detail information and texture features. At the same time, in order to suppress background noise, this paper designs a multi-level feature gradient flow optimization module (C2f_CA, abbreviated as CCA) that integrates coordinate attention and a Cross-Stage Partial Frequency-domain Omni-Kernel module (CSPFOK) to enhance feature extraction capability. Finally, the SCYLLA-IoU (SIoU) optimization model training process was introduced. The experimental results showed that EP-YOLO achieved 97.5% mAP50 on the PKU-Market-PCB dataset and 98.5% mAP50 on the DeepPCB dataset, with a parameter reduction of approximately 12.55%, outperforming popular object detection networks. The results highlight the potential capabilities of EP-YOLO, providing a powerful and effective solution for industrial PCB defect detection.

Schlagwörter

Stichwörter der Autor:innen

PCBYOLOv8deep learningdefect detectionsmall goals

Autor:innen und Institutionen

  • School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China.
  • Earthwork Collaborative Innovation Center, Liuzhou 545006, China.
  • Engineering Research Center of Advanced Engineering Equipment, University of Guangxi, Liuzhou 545006, China.
  • Guangxi Low-Altitude Unmanned Aircraft Key Technologies Engineering Research Center, Liuzhou 545616, China.

ORCID-Profile: Xiangsuo Fan, Can Yang

Förderung

  • the Guangxi Key Research and Development Program
  • the research project funded by Natural Science Foundation of Guangxi Zhuang Autonomous Region
  • Natural Science Foundation of Guangxi Zhuang Autonomous Region
  • Guangxi Key Research and Development Program

Zitieren

APA

Fan, X., Yang, C., & Yu, L. (2026). EP-YOLO: A Printed Circuit Board Defect Detection Network Integrating Coordinate Attention and Multi-Level Gradient Flow Optimization. Sensors, 26(10), 3106. https://doi.org/10.3390/s26103106

Vancouver

Fan X, Yang C, Yu L. EP-YOLO: A Printed Circuit Board Defect Detection Network Integrating Coordinate Attention and Multi-Level Gradient Flow Optimization. Sensors. 2026;26(10):3106. doi:10.3390/s26103106

BibTeX
@article{Fan2026,
  author = {Fan, Xiangsuo and Yang, Can and Yu, Ling},
  title = {EP-YOLO: A Printed Circuit Board Defect Detection Network Integrating Coordinate Attention and Multi-Level Gradient Flow Optimization},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3106},
  doi = {10.3390/s26103106}
}
Kostenlos starten →