Small PCB Defect Detection Based on Convolutional Block Attention Mechanism and YOLOv8
Applied Sciences · 21.01.2026 · 16 (2) · 1078
DOI: 10.3390/app16021078 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.01.2026. Verfasst von Zhe Sun und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Automated defect detection in printed circuit boards (PCBs) is a critical process for ensuring the quality and reliability of electronic products. To address the limitations of existing detection methods, such as insufficient sensitivity to minor defects and limited recognition accuracy in complex backgrounds, this paper proposes an enhanced YOLOv8 detection framework. The core contribution lies not merely in the integration of the Convolutional Block Attention Module (CBAM), but in a principled and task-specific integration strategy designed to address the multi-scale and low-contrast nature of PCB defects. The complete CBAM is integrated into the multi-scale feature layers (P3, P4, P5) of the YOLOv8 backbone network. By leveraging sequential channel and spatial attention submodules, CBAM guides the model to dynamically optimise feature responses, thereby significantly enhancing feature extraction for tiny, morphologically diverse defects. Experiments on a public PCB defect dataset demonstrate that the proposed model achieves a mean average precision (mAP@50) of 98.8% while maintaining real-time inference speed, surpassing the baseline YOLOv8 model by 9.5%, with the improvements of 7.4% in precision and 12.3% in recall. While the model incurs a higher computational cost (79.4 GFLOPs), it maintains a real-time inference speed of 109.11 FPS, offering a viable trade-off between accuracy and efficiency for high-precision industrial inspection. The proposed model demonstrates superior performance in detecting small-scale defects, making it highly suitable for industrial deployment.
Zitieren
APA
Sun, Z., Ma, R., & Lei, Q. (2026). Small PCB Defect Detection Based on Convolutional Block Attention Mechanism and YOLOv8. Applied Sciences, 16(2), 1078. https://doi.org/10.3390/app16021078
Vancouver
Sun Z, Ma R, Lei Q. Small PCB Defect Detection Based on Convolutional Block Attention Mechanism and YOLOv8. Applied Sciences. 2026;16(2):1078. doi:10.3390/app16021078
BibTeX
@article{Sun2026,
author = {Sun, Zhe and Ma, Ruihan and Lei, Qujiang},
title = {Small PCB Defect Detection Based on Convolutional Block Attention Mechanism and YOLOv8},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {2},
pages = {1078},
doi = {10.3390/app16021078}
}
EUVIMED