Soldering Defect Segmentation Method for PCB on Improved UNet
Applied Sciences · 21.08.2024 · 14 (16) · 7370
DOI: 10.3390/app14167370 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.08.2024. Verfasst von Zhongke Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Academician (Expert) Workstation Fund Project of Sichuan Province of China, Special Fund for Training High Level Innovative Talents of Sichuan University of Science and Engineering, Sichuan University of Science and Engineering for Talent introduction project.
Abstract (Originalsprache)
Despite being indispensable devices in the electronic manufacturing industry, printed circuit boards (PCBs) may develop various soldering defects in the production process, which seriously affect the product’s quality. Due to the substantial background interference in the soldering defect image and the small and irregular shapes of the defects, the accurate segmentation of soldering defects is a challenging task. To address this issue, a method to improve the encoder–decoder network structure of UNet is proposed for PCB soldering defect segmentation. To enhance the feature extraction capabilities of the encoder and focus more on deeper features, VGG16 is employed as the network encoder. Moreover, a hybrid attention module called the DHAM, which combines channel attention and dynamic spatial attention, is proposed to reduce the background interference in images and direct the model’s focus more toward defect areas. Additionally, based on GSConv, the RGSM is introduced and applied in the decoder to enhance the model’s feature fusion capabilities and improve the segmentation accuracy. The experiments demonstrate that the proposed method can effectively improve the segmentation accuracy for PCB soldering defects, achieving an mIoU of 81.74% and mPA of 87.33%, while maintaining a relatively low number of model parameters at only 22.13 M and achieving an FPS of 30.16, thus meeting the real-time detection speed requirements.
Förderung
- Academician (Expert) Workstation Fund Project of Sichuan Province of China
- Special Fund for Training High Level Innovative Talents of Sichuan University of Science and Engineering
- Sichuan University of Science and Engineering for Talent introduction project
- Project of Sichuan University of Science and Engineering for Research on the Ideological and Political Construction of Machine Learning Curriculum
- Innovation Fund of Postgraduate, Sichuan University of Science & Engineering
Zitieren
APA
Li, Z., & Liu, X. (2024). Soldering Defect Segmentation Method for PCB on Improved UNet. Applied Sciences, 14(16), 7370. https://doi.org/10.3390/app14167370
Vancouver
Li Z, Liu X. Soldering Defect Segmentation Method for PCB on Improved UNet. Applied Sciences. 2024;14(16):7370. doi:10.3390/app14167370
BibTeX
@article{Li2024,
author = {Li, Zhongke and Liu, Xiaofang},
title = {Soldering Defect Segmentation Method for PCB on Improved UNet},
journal = {Applied Sciences},
year = {2024},
volume = {14},
number = {16},
pages = {7370},
doi = {10.3390/app14167370}
}
EUVIMED