MDEB-YOLO: A Lightweight Multi-Scale Attention Network for Micro-Defect Detection on Printed Circuit Boards
Micromachines · 30.01.2026 · 17 (2) · 192
DOI: 10.3390/mi17020192 ↗Kurz gefasst
Fachartikel in der Zeitschrift Micromachines, online erschienen am 30.01.2026. Verfasst von Xun Zuo und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hubei University of Economics Youth Fund, the College Student Innovation and Entrepreneurship Training Program of China, the Scientific Research Plan of Hubei Provincial Department of Education (Guiding Project).
Abstract (Originalsprache)
Defect detection on Printed Circuit Boards (PCBs) constitutes a pivotal component of the quality control system in electronics manufacturing. However, owing to the intricate circuitry structures on PCB surfaces and the characteristics of defects—specifically their minute scale, irregular morphology, and susceptibility to background texture interference—existing generic deep learning models frequently fail to achieve an optimal equilibrium between detection accuracy and inference speed. To address these challenges, this study proposes MDEB-YOLO, a lightweight real-time detection network tailored for PCB micro-defects. First, to enhance the model’s perceptual capability regarding subtle geometric variations along conductive line edges, we designed the Efficient Multi-scale Deformable Attention (EMDA) module within the backbone network. By integrating parallel cross-spatial channel learning with deformable offset networks, this module achieves adaptive extraction of irregular concave–convex defect features while effectively suppressing background noise. Second, to mitigate feature loss of micro-defects during multi-scale transformations, a Bidirectional Residual Multi-scale Feature Pyramid Network (BRM-FPN) is proposed. Utilizing bidirectional weighted paths and residual attention mechanisms, this network facilitates the efficient fusion of multi-view features, significantly enhancing the representation of small targets. Finally, the detection head is reconstructed based on grouped convolution strategies to design the Lightweight Grouped Convolution Head (LGC-Head), which substantially reduces parameter volume and computational complexity while maintaining feature discriminability. The validation results on the PKU-Market-PCB dataset demonstrate that MDEB-YOLO achieves a mean Average Precision (mAP) of 95.9%, an inference speed of 80.6 FPS, and a parameter count of merely 7.11 M. Compared to baseline models, the mAP is improved by 1.5%, while inference speed and parameter efficiency are optimized by 26.5% and 24.5%, respectively; notably, detection accuracy for challenging mouse bite and spur defects increased by 3.7% and 4.0%, respectively. The experimental results confirm that the proposed method outperforms state-of-the-art approaches in both detection accuracy and real-time performance, possessing significant value for industrial applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China.
- School of Information Engineering, Wuhan Huaxia Institute of Technology, Wuhan 430223, China.
- School of Information Engineering, Hubei University of Economics, Wuhan 430205, China.
- Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, Wuhan 430205, China.
ORCID-Profile: Ke Wang, Jianmin Hu
Förderung
- Hubei University of Economics Youth Fund
- the College Student Innovation and Entrepreneurship Training Program of China
- the Scientific Research Plan of Hubei Provincial Department of Education (Guiding Project)
- College Student Innovation and Entrepreneurship Training Program of China
- Scientific Research Plan of Hubei Provincial Department of Education
Zitieren
APA
Zuo, X., Zhao, N., Wang, K., & Hu, J. (2026). MDEB-YOLO: A Lightweight Multi-Scale Attention Network for Micro-Defect Detection on Printed Circuit Boards. Micromachines, 17(2), 192. https://doi.org/10.3390/mi17020192
Vancouver
Zuo X, Zhao N, Wang K, Hu J. MDEB-YOLO: A Lightweight Multi-Scale Attention Network for Micro-Defect Detection on Printed Circuit Boards. Micromachines. 2026;17(2):192. doi:10.3390/mi17020192
BibTeX
@article{Zuo2026,
author = {Zuo, Xun and Zhao, Ning and Wang, Ke and Hu, Jianmin},
title = {MDEB-YOLO: A Lightweight Multi-Scale Attention Network for Micro-Defect Detection on Printed Circuit Boards},
journal = {Micromachines},
year = {2026},
volume = {17},
number = {2},
pages = {192},
doi = {10.3390/mi17020192}
}
EUVIMED