Makine Öğrenmesi ve Derin Öğrenme Algoritmaları ile Baskı Devre Kartlarındaki Kusurların Tespiti

Öz

Baskı devre kartları (PCB), elektronik bileşenleri bir arada tutan ve bu bileşenler arasındaki elektrik bağlantısını sağlayan elektronik devre kartlarıdır. Baskı devre kartları, dayanıklılık, daha az ısınma, minimum kablo kullanımı ve montaj kolaylığı gibi geleneksel kablolu devrelere göre birçok avantaj sunmaktadır. Baskı devre kartlarının doğru tasarımı ve üretimi baskı devre kartlarının kalitesini ve verimliliğini önemli ölçüde etkilemektedir. Bu çalışmada baskı devre kartlarının doğru bir şekilde üretilmesine ve hata oranının en aza indirilmesine yardımcı olmak için makine öğrenmesi ve derin öğrenme algoritmalarına dayalı kusur tespit sistemi önerilmiştir. Önerilen sistemde baskı devre üzerinde yer alan eksik delik, fare ısırığı, açık devre, kısa devre, çıkıntı ve sahte bakır kusurları tespit edilmiştir. Elde edilen sonuçlara göre YOLO-v4 ile %74.62, HOG+SVM ile %47.83, HOG+KNN ile %39.86 başarı doğrulukları elde edilmiştir. Çalışmada ele alınan algoritmaların baskı devre kartlarında kusur tespitinde uygulanabilir olduğu görülmüştür.

Anahtar Kelimeler

• Yapay zeka
• Makine öğrenmesi
• Derin öğrenme
• Baskı devre kartı.

Detection of Defects in Printed Circuit Boards with Machine Learning and Deep Learning Algorithms

Abstract

Printed Circuit Boards (PCBs) are electronic boards that hold electronic components together and provide the electrical connection between these components. Printed circuit boards offer many advantages over traditional wired circuits, such as durability, less heat, minimal wiring, and ease of assembly. Correct design and production of printed circuit boards significantly affect the quality and efficiency of printed circuit boards. In this study, a defect detection system based on machine learning and deep learning algorithms is proposed to help produce printed circuit boards accurately and minimize the error rate. In the proposed system, missing hole, mouse bite, open circuit, short, spur, and spurious copper defects on the printed circuit have been determined. According to the results obtained, According to the results obtained, success accuracies of 74.62% were obtained with YOLO-v4, 47.83% with HOG+SVM, and 39.86% with HOG+KNN. It has been seen that the algorithms discussed in the study are applicable in the detection of defects in printed circuit boards.

Keywords

• Artificial intelligence
• Machine learning
• Deep learning
• Printed circuit board

Kaynakça

1. Adibhatla, V. A., Chih, H. C., Hsu, C. C., Cheng, J., Abbod, M. F., & Shieh, J. S. (2020). Defect detection in printed circuit boards using you-only-look-once convolutional neural networks. Electronics, 9(9), 1547. https://doi.org/10.3390/electronics9091547
2. Adibhatla, V. A., Shieh, J. S., Abbod, M. F., Chih, H. C., Hsu, C. C., & Cheng, J. (2018). Detecting defects in PCB using deep learning via convolution neural networks. In 2018 13th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT) (pp. 202-205). https://doi.org/10.1109/IMPACT.2018.8625828
3. Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
4. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152). https://doi.org/10.1145/130385.130401
5. Colab (2022). “Google Colaboratory”, Retrieved in September, 03, 2022 from https://colab.research.google.com
6. Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27. https://doi.org/10.1109/TIT.1967.1053964
7. Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), 1, 886-893. https://doi.org/10.1109/CVPR.2005.177
8. Deng, Y. S., Luo, A. C., & Dai, M. J. (2018). Building an automatic defect verification system using deep neural network for pcb defect classification. In 2018 4th International Conference on Frontiers of Signal Processing (ICFSP) (pp. 145-149). https://doi.org/10.1109/ICFSP.2018.8552045

9. Ding, R., Dai, L., Li, G., & Liu, H. (2019). TDD‐net: a tiny defect detection network for printed circuit boards. CAAI Transactions on Intelligence Technology, 4(2), 110-116. https://doi.org/10.1049/trit.2019.0019
10. Fung, V. W., & Yung, K. C. (2020). An intelligent approach for improving printed circuit board assembly process performance in smart manufacturing. International Journal of Engineering Business Management, 12, 1847979020946189. https://doi.org/10.1177/1847979020946189
11. Hu, B., & Wang, J. (2020). Detection of PCB surface defects with improved faster-RCNN and feature pyramid network. IEEE Access, 8, 108335-108345. https://doi.org/10.1109/ACCESS.2020.3001349
12. Hua, G., Huang, W., & Liu, H. (2018). Accurate image registration method for PCB defects detection. The Journal of Engineering, 2018(16), 1662-1667. https://doi.org/10.1049/joe.2018.8272
13. Huang, W., & Wei, P. (2019). A PCB dataset for defects detection and classification. arXiv preprint arXiv:1901.08204
14. Kaggle, (2022). “Kaggle”, Retrieved in September, 01, 2022 from https://www.kaggle.com/datasets/akhatova/pcb-defects
15. Liu, G., & Wen, H. (2021). Printed circuit board defect detection based on MobileNet-Yolo-Fast. Journal of Electronic Imaging, 30(4), 043004. https://doi.org/10.1117/1.JEI.30.4.043004
16. Santoso, A. D., Cahyono, F. B., Prahasta, B., Sutrisno, I., & Khumaidi, A. (2022). Development of PCB Defect Detection System Using Image Processing With YOLO CNN Method. International Journal of Artificial Intelligence Research, 6(1).
17. Sezer, A., & Altan, A. (2021). Detection of solder paste defects with an optimization‐based deep learning model using image processing techniques. Soldering & Surface Mount Technology. https://doi.org/10.1108/SSMT-04-2021-0013
18. Tang, S., He, F., Huang, X., & Yang, J. (2019). Online PCB defect detector on a new PCB defect dataset. arXiv preprint arXiv:1902.06197
19. Tsai, D. M., & Huang, C. K. (2018). Defect detection in electronic surfaces using template-based Fourier image reconstruction. IEEE Transactions on Components, Packaging and Manufacturing Technology, 9(1), 163-172. https://doi.org/10.1109/TCPMT.2018.2873744
20. Volkau, I., Mujeeb, A., Wenting, D., Marius, E., & Alexei, S. (2019). Detection defect in printed circuit boards using unsupervised feature extraction upon transfer learning. In 2019 International Conference on Cyberworlds (CW) (pp. 101-108). https://doi.org/10.1109/CW.2019.00025
21. Zhang, C., Shi, W., Li, X., Zhang, H., & Liu, H. (2018). Improved bare PCB defect detection approach based on deep feature learning. The Journal of Engineering, 2018(16), 1415-1420. https://doi.org/10.1049/joe.2018.8275
22. Zhang, L., Jin, Y., Yang, X., Li, X., Duan, X., Sun, Y., & Liu, H. (2018). Convolutional neural network‐based multi‐label classification of PCB defects. The Journal of Engineering, 2018(16), 1612-1616. https://doi.org/10.1049/joe.2018.8279