A Novel Contrastive Self-Supervised Learning Framework for Solving Data Imbalance in Solder Joint Defect Detection
Entropy · 31.01.2023 · 25 (2) · 268
DOI: 10.3390/e25020268 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 31.01.2023. Verfasst von Jing Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program in Jiangsu Province, Young Scientists Fund of the National Natural Science Foundation of China.
Abstract (Originalsprache)
Poor chip solder joints can severely affect the quality of the finished printed circuit boards (PCBs). Due to the diversity of solder joint defects and the scarcity of anomaly data, it is a challenging task to automatically and accurately detect all types of solder joint defects in the production process in real time. To address this issue, we propose a flexible framework based on contrastive self-supervised learning (CSSL). In this framework, we first design several special data augmentation approaches to generate abundant synthetic, not good (sNG) data from the normal solder joint data. Then, we develop a data filter network to distill the highest quality data from sNG data. Based on the proposed CSSL framework, a high-accuracy classifier can be obtained even when the available training data are very limited. Ablation experiments verify that the proposed method can effectively improve the ability of the classifier to learn normal solder joint (OK) features. Through comparative experiments, the classifier trained with the help of the proposed method can achieve an accuracy of 99.14% on the test set, which is better than other competitive methods. In addition, its reasoning time is less than 6 ms per chip image, which is in favor of the real-time defect detection of chip solder joints.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China.
ORCID-Profile: Jing Zhou
Förderung
- Key Research and Development Program in Jiangsu Province
- Young Scientists Fund of the National Natural Science Foundation of China
Zitieren
APA
Zhou, J., Li, G., Wang, R., Chen, R., & Luo, S. (2023). A Novel Contrastive Self-Supervised Learning Framework for Solving Data Imbalance in Solder Joint Defect Detection. Entropy, 25(2), 268. https://doi.org/10.3390/e25020268
Vancouver
Zhou J, Li G, Wang R, Chen R, Luo S. A Novel Contrastive Self-Supervised Learning Framework for Solving Data Imbalance in Solder Joint Defect Detection. Entropy. 2023;25(2):268. doi:10.3390/e25020268
BibTeX
@article{Zhou2023,
author = {Zhou, Jing and Li, Guang and Wang, Ruifeng and Chen, Ruiyang and Luo, Shouhua},
title = {A Novel Contrastive Self-Supervised Learning Framework for Solving Data Imbalance in Solder Joint Defect Detection},
journal = {Entropy},
year = {2023},
volume = {25},
number = {2},
pages = {268},
doi = {10.3390/e25020268}
}
EUVIMED