Affiliation:
1. College of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China
Abstract
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.
Funder
National Natural Science Foundation of China
Young Scientists Fund of the National Natural Science Foundation of China
Subject
General Physics and Astronomy
Reference48 articles.
1. PCBNet: A Lightweight Convolutional Neural Network for Defect Inspection in Surface Mount Technology;Wu;IEEE Trans. Instrum. Meas.,2022
2. Kuttiyil Thomas, O.T., and Gopalan, P.P. (2022). Electronics Production Defects and Analysis, Springer.
3. Schubeck, J., Koblah, D., Botero, U.J., and Forte, D. (2023, January 22). A Comprehensive Taxonomy of PCB Defects. Available online: https://dforte.ece.ufl.edu/wp-content/uploads/sites/65/2022/02/A_Comprehensive_Taxonomy_of_PCB_Defects.pdf.
4. Deep Siamese Semantic Segmentation Network for PCB Welding Defect Detection;Ling;IEEE Trans. Instrum. Meas.,2022
5. Dorj, E., Chen, C., and Pecht, M. (2013, January 2–9). A bayesian hidden markov model-based approach for anomaly detection in electronic systems. Proceedings of the 2013 IEEE Aerospace Conference, Big Sky, MT, USA.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献