Solder Joint Defect Detection in the Connectors Using Improved Faster-RCNN Algorithm
Source abstract
Abstract
The miniaturization and high integration of electronic products have higher and higher requirements for welding of internal components of electronic products. A welding quality detection method has always been one of the important research contents in the industry, among which, the research on solder joint defect detection of a connector has gradually attracted people’s attention with the development of image detection algorithm. The traditional solder joint detection method of connector adopts manual detection or automatic detection methods, which is inefficient and not safe enough. With the development of deep learning, the application of a deep convolutional neural network to target detection has become a research hotspot. In this paper, a data set of connector solder joint samples was made and the number of image samples was expanded to more than 3 times of the original by using data augmentation. Clustering generates anchor boxes and transfer learning with ResNet-101 were fused, so an improved faster region-based convolutional neural networks (Faster RCNN) algorithm was proposed. The experiment verified that the improved algorithm proposed in this paper had a great improvement in all aspects compared with the original algorithm. The average detection accuracy of this method can reach 94%, and the detection rate of some defects can even reach 100%, which can completely meet the industrial requirements.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Thermography and Photoacoustic Techniques · Digital Transformation in Industry
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Ministry of Education, Beijing 100044, China
Key Laboratory of Vehicle Advanced Manufacturing, Measuring and Control Technology, School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Ministry of Education, Beijing 100044, China
References (30)
Show source-provided references
1. Lei, X. (2020). Research on Qualification Detection of Cable Joint Solder Joint Based on Deep Learning, Lanzhou University of Technology.
2. Furlanetto, V., Stocco, D., and Batalha, G.F. (2011, January 28–31). Electric resistance spot welding evaluation by A-scan and B-scan ultrasound analyses. Proceedings of the AIP Conference, American Institute of Physics, College Park, MD, USA.10.1063/1.3552551 ↗
3. Research on defects inspection of solder balls based on eddy current pulsed thermography10.3390/s151025882 ↗
4. Statistical process monitoring system for SMT industry using automatic optical inspection system10.4028/www.scientific.net/MSF.580-582.561 ↗
5. The deficiency recognition in PCBA`s automatic optical inspection system by using back-propagation network method10.3923/jas.2008.2814.2824 ↗
6. Development of an automatic optical inspection system and its application to defect examination
7. Automatic optical inspection system for IC molding surface10.1007/s10845-014-0924-5 ↗
8. Review on automated optical (visual) inspection and its applications in defect detection
9. Wu, F., Zhang, X., Kuan, Y., and He, Z. (2008, January 25–27). An AOI algorithm for PCB based on feature extraction. Proceedings of the 7th World Congress on Intelligent Control and Automation, Chongqing, China.
10. PCB welding spot detection with image processing method based on automatic threshold image segmentation algorithm and mathematical morphology10.1108/CW-08-2015-0039 ↗
11. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
12. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
13. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (July, January 26). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
14. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2015, January 7–13). SSD: Single shot MultiBox detector. Proceedings of the European Conference on Computer Vision, Santiago, Chile.10.1007/978-3-319-46448-0_2 ↗
15. Airport detection based on improved faster RCNN in large scale remote sensing images
16. Mo, N., and Yan, L. (2020). Improved faster RCNN based on feature amplification and oversampling data augmentation for oriented vehicle detection in aerial images. Remote. Sens., 12.10.3390/rs12162558 ↗
17. Image fire detection algorithms based on convolutional neural networks10.1016/j.csite.2020.100625 ↗
18. Ju, M., Luo, H., Wang, Z., Hui, B., and Chang, Z. (2019). The application of improved YOLO V3 in multi-scale target detection. Appl. Sci., 9.10.3390/app9183775 ↗
19. Ding, F., Zhuang, Z., Liu, Y., Jiang, D., Yan, X., and Wang, Z. (2020). Detecting defects on solid wood panels based on an improved SSD algorithm. Sensors, 20.10.3390/s20185315 ↗
20. An enhanced SSD with feature fusion and visual reasoning for object detection10.1007/s00521-018-3486-1 ↗
21. One class based feature learning approach for defect detection using deep autoencoders10.1016/j.aei.2019.100933 ↗
22. Li, J., Gu, J., Huang, Z., and Wen, J. (2019). Application research of improved YOLO V3 algorithm in PCB electronic component detection. Appl. Sci., 9.10.3390/app9183750 ↗
23. Urbonas, A., Raudonis, V., Maskeliūnas, R., and Damaševičius, R. (2019). Automated identification of wood veneer surface defects using faster region-based convolutional neural network with data augmentation and transfer learning. Appl. Sci., 9.10.3390/app9224898 ↗
24. Faster multi-defect detection system in shield tunnel using combination of FCN and faster RCNN10.1177/1369433219849829 ↗
25. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
26. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 8–16). Identity Mappings in Deep Residual Networks. Proceedings of the ECCV 2016: Computer Vision—ECCV 2016, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_38 ↗
27. Image classification based on RESNET
28. Protein contact map prediction based on ResNet and DenseNet
29. One-shot learning gesture recognition based on joint training of 3D ResNet and memory module10.1007/s11042-019-08429-9 ↗
30. Wang, A., Wang, M., Wu, H., Jiang, K., and Iwahori, Y. (2020). A novel LiDAR data classification algorithm combined CapsNet with ResNet. Sensors, 20.10.3390/s20041151 ↗