PCB Üretiminde Çok Sınıflı Kusur Tespiti için YOLO Tabanlı Derin Öğrenme Modeli

Year 2025, Volume: 25 Issue: 4, 816 - 826, 04.08.2025

İzemnur Budak , Sezen Bal , Hayriye Korkmaz

https://doi.org/10.35414/akufemubid.1551996

Abstract

Bu çalışmada, PCB üretim sürecinde karşılaşılan olası kusurları otomatik olarak tespit ederek insan kaynaklı hataları en aza indirmeyi ve üretim sürecini hızlandırmayı amaçlayan; görüntü işleme tekniklerini ve derin öğrenme algoritmalarını kullanan bir kusur tespit ve sınıflandırma yöntemi önerilmiştir. Özellikle PCB üretim hattında böyle derin öğrenme tabanlı bir sistemin uygulanabilirliği değerlendirilmiş ve bu doğrultuda gerçek zamanlı bir simülasyon gerçekleştirilmiştir.
Bu çalışmada farklı kusur türlerini içeren görüntülerden oluşan açık kaynaklı DeepPCB veri seti içinde yer alan 1194 PCB görüntüsü kullanılmıştır. Veri setinde yer alan görüntüler üzerinde toplam 7897 kusur etiketlenmiş ve bunlardan 6385 adedi (%80) eğitim, 1512 (%20) adedi ise test için ayrılmıştır. Eğitim ve test setleri, sınıflar arasında dengeli bir dağılım olacak şekilde rastgele bölünmüştür. Kusurlar, MakeSense yazılımı kullanılarak etiketlenmiş ve bu süreçte altı farklı kusur türü tanımlanmıştır. Etiketleme işlemi, modelin eğitim aşamasında yüksek doğruluk elde edilmesinde kritik bir adım olarak değerlendirilmiştir.
YOLOv4 algoritmasıyla eğitilen model, mAP@50 değeri %64,1 olarak hesaplanmıştır. Daha güncel bir algoritma olan YOLOv8 kullanılarak eğitilen modelde ise mAP@50 değeri %93,5'e ulaşmıştır. Bu sonuçlar, YOLOv8 algoritmasının, PCB üretim hatlarında yüksek doğruluk oranı ve daha az hata ile uygulanabilir bir çözüm sunduğunu göstermektedir. Diğer taraftan bu modellerde, YOLOv4 ve v8’in varsayılan standart parametreleri kullanılmıştır. Ancak literatür taraması yapıldığında bu parametrelerin optimize edilmesinin daha yüksek performans elde edilmesinde önemli bir payı olduğu görülmüştür.

Keywords

Kusur Tespiti , PCB , Görüntü İşleme , Derin Öğrenme , Gerçek Zamanlı Uygulama , Üretim Hattı Otomasyonu

YOLO-Based Deep Learning Model for Multi-Class Defect Detection in the PCB Manufacturing

Abstract

In this study, a defect detection and classification method using image processing techniques and deep learning algorithms is proposed, which aims to minimize human-induced errors and speed up the production process by automatically detecting possible defects encountered in the PCB production process. In particular, the applicability of such a deep learning-based system in the PCB production line was evaluated and a real-time simulation was performed in this direction.
In this study, 1194 PCB images were used in the open-source DeepPCBdataset, which consists of images containing different types of defects. A total of 7897 defects were labeled on the images in the data set, of which 6385 (80%) were reserved for training and 1512 (20%) for testing. The training and test sets were randomly divided to provide a balanced distribution among the classes. Defects were labeled using Make Sense software and six different defect types were identified during this process. The labeling process was considered a critical step in achieving high accuracy during the training phase of the model.
The model trained with the YOLOv4 algorithm had a mAP@50 value of 64.1%. In the model trained using YOLOv8, a more up-to-date algorithm, the mAP@50 value reached 93.5%. These results show that the YOLOv8 algorithm offers a viable solution with high accuracy and fewer errors in PCB production lines. On the other hand, the default standard parameters of YOLOv4 and v8 were used in these models. However, when the literature was reviewed, it was seen that optimizing these parameters had an important share in achieving higher performance.

Keywords

Defect Detection , PCB , Image Processing , Deep Learning , Real-Time Application , Manufacturing Line Automation

References

• Adibhatla, V. A., Chih, H. C., Hsu, C. C., Cheng, J., Abbod, M. F., & Shieh, J. S., 2021. Applying deep learning to defect detection in printed circuit boards via a newest model of you-only-look-once.
• Mathematical Biosciences and Engineering, 18,4, 4411-4428
• https://doi.org/10.3934/mbe.2021223
• Ameri, R., Hsu, C. C., & Band, S. S., 2024. A systematic review of deep learning approaches for surface defect detection in industrial applications. Engineering Applications of Artificial Intelligence, 130, 107717.
• https://doi.org/10.1016/j.engappai.2023.107717
• Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M., 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
• https://doi.org/10.48550/arXiv.2004.10934 Chen, Z., Zhu, Q., Zhou, X., Deng, J., & Song, W., 2024. Experimental Study on YOLO-Based Leather Surface Defect Detection. IEEE Access, 12, 32830-32848 https://doi.org/10.1109/ACCESS.2024.3369705 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.
• http://dx.doi.org/10.1049/trit.2019.0019 Du, M., Chen, M., Cao, X., & Takamasu, K., 2024. Deep Learning-Based Multi-Species Appearance Defect Detection Model for MLCC. Ieee Transactions on Instrumentation and Measurement,73
• https://doi.org/10.1109/TIM.2024.3375957
• Hassan, M. H., Reiter, E., & Razzaq, M., 2024. Automatic ovarian follicle detection using object detection models.
• http://dx.doi.org/10.21203/rs.3.rs-4637709/v1 Kim, J., Ko, J., Choi, H., & Kim, H., 2021. Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder. Sensors, 21(15), 4968.
• https://doi.org/10.3390/s21154968
• Li, W. H., Zhang, H. O., Wang, G. L., Xiong, G., Zhao, M. H., Li, G. K., & Li, R. S., 2023. Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing. Robotics and Computer-Integrated Manufacturing, 80, 12.
• http://dx.doi.org/10.1016/j.rcim.2022.102470 Li, Z., Chen, J., Huang, H., & Dong, X., 2023. Defect Detection in Computer Motherboard Assembly through Fusion of Multi-Scale Features and Attention Mechanisms. Paper presented at the 2023 9th International Conference on Systems and Informatics (ICSAI).
• http://dx.doi.org/10.1109/ICSAI61474.2023.10423311 Liao, X., Lv, S., Li, D., Luo, Y., Zhu, Z., & Jiang, C., 2021. YOLOv4-MN3 for PCB surface defect detection. Applied Sciences, 11(24), 11701.
• https://doi.org/10.3390/app112411701
• Lin, Q., Zhou, J., Ma, Q., Ma, Y., Kang, L., & Wang, J., 2022. EMRA-Net: A pixel-wise network fusing local and global features for tiny and low-contrast surface defect detection. IEEE Transactions on Instrumentation and Measurement, 71, 1-14.
• https://doi.org/10.1109/TIM.2022.3151926 Ling, Q., & Isa, N. A. M., 2023. Printed circuit board defect detection methods based on image processing, machine learning and deep learning: A survey. Ieee Access, 11, 15921-15944.
• https://doi.org/10.1109/ACCESS.2023.3245093
• Luo, J., Yang, Z., Li, S., & Wu, Y., 2021. FPCB surface defect detection: A decoupled two-stage object detection framework. Ieee Transactions on Instrumentation and Measurement, 70, 1-11.
• http://dx.doi.org/10.1109/TIM.2021.3092510 Mahrishi, M., Morwal, S., Muzaffar, A. W., Bhatia, S., Dadheech, P., & Rahmani, M. K. I., 2021. Video index point detection and extraction framework using custom YoloV4 Darknet object detection model. Ieee Access, 9, 143378-143391.
• http://dx.doi.org/10.1109/ACCESS.2021.3118048 Ocepek, M., Žnidar, A., Lavrič, M., Škorjanc, D., & Andersen, I. L., 2021. DigiPig: First developments of an automated monitoring system for body, head and tail detection in intensive pig farming. Agriculture, 12(1), 2.
• https://doi.org/10.3390/agriculture12010002 Redmon, J., 2016. You only look once: Unified, real-time object detection. IEEE conference on computer vision and pattern recognition. 779-788
• https://doi.org/10.1109/CVPR.2016.91 Sharma, V. K., & Mir, R. N., 2020. A comprehensive and systematic look up into deep learning based object detection techniques: A review. Computer Science Review, 38, 100301.
• http://dx.doi.org/10.1016/j.cosrev.2020.100301
• 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, 33(5), 291-298.
• https://doi.org/10.1108/SSMT-04-2021-0013 Subramanyam, V., Kumar, J., & Singh, S. N., 2022. Temporal synchronization framework of machine-vision cameras for high-speed steel surface inspection systems. Journal of Real-Time Image Processing, 19(2), 445-461. http://dx.doi.org/10.1007/s11554-022-01198-z
• Tang, S., He, F., Huang, X., & Yang, J., 2019. Online PCB defect detector on a new PCB defect dataset. arXiv preprint arXiv:1902.06197. https://doi.org/10.48550/arXiv.1902.06197
• Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A., 2023. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Machine Learning and Knowledge Extraction, 5(4), 1680-1716. https://doi.org/10.3390/make5040083
• LI, W., 2024. Detecting defects in PCB manufacturing: an exploration using Yolov8 deep learning. International Journal on Interactive Design and Manufacturing (IJIDeM), 1-11. https://doi.org/10.1007/s12008-024-01986-w Wang, X., Zhang, H., Liu, Q., Gong, W., Bai, S., & You, H., 2024. YOLO’s multiple-strategy PCB defect detection model. IEEE MultiMedia. https://doi.org/10.1109/mmul.2024.3359267
• Xie, Y., Hu, W., Xie, S., & He, L., 2023. Surface defect detection algorithm based on feature-enhanced YOLO. Cognitive Computation, 15(2), 565-579. https://doi.org/10.1007/s12559-022-10061-z
• Xuan, W., Jian-She, G., Bo-Jie, H., Zong-Shan, W., Hong-Wei, D., & Jie, W., 2022. A lightweight modified YOLOX network using coordinate attention mechanism for PCB surface defect detection. IEEE sensors journal, 22(21), 20910-20920. https://doi.org/10.1109/JSEN.2022.3208580 Zhang, Q., & Liu, H., 2021. Multi-scale defect detection of printed circuit board based on feature pyramid network, 31, 1, 76-87. http://dx.doi.org/10.1109/MMUL.2024.3359267
• Zhang, Y., Xie, F., Huang, L., Shi, J., Yang, J., & Li, Z., 2021. A lightweight one-stage defect detection network for small object based on dual attention mechanism and PAFPN. Frontiers in Physics, 9, 708097. http://dx.doi.org/10.3389/fphy.2021.708097
• Budak,İ. Gerçek Zamanlı PCB Kusur Tespiti [Video dosyası]. https://drive.google.com/drive/folders/1fS9EMJAtJaci67d6lKK-qT6VJc5-4Vj_?usp=sharing (25.11. 2024)
• Make Sense, https://www.makesense.ai/, (10.08. 2024)
• Labelbox, https://labelbox.com/, (10.08. 2024)
• LabelImg, https://medium.com/@pat.x.guillen/setting-up-labelimg-1ad1887d91c5, (10.08. 2024)
• Labelme, https://github.com/labelmeai/labelme, (10.08. 2024)
• Roboflow, https://roboflow.com/, (10.08. 2024)
• SuperAnnotate, https://superannotate.medium.com/introduction-to-object-detection-with-deep-learning-f4d2b9f4d1b5, (10.08. 2024)
• Supervisely, https://supervisely.com/labeling-toolbox/images/, (10.08. 2024)
• Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A., 2023. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Machine Learning and Knowledge Extraction, 5(4), 1680-1716. https://doi.org/10.3390/make5040083
• LI, W., 2024. Detecting defects in PCB manufacturing: an exploration using Yolov8 deep learning. International Journal on Interactive Design and Manufacturing (IJIDeM), 1-11. https://doi.org/10.1007/s12008-024-01986-w Wang, X., Zhang, H., Liu, Q., Gong, W., Bai, S., & You, H., 2024. YOLO’s multiple-strategy PCB defect detection model. IEEE MultiMedia. https://doi.org/10.1109/mmul.2024.3359267
• Xie, Y., Hu, W., Xie, S., & He, L., 2023. Surface defect detection algorithm based on feature-enhanced YOLO. Cognitive Computation, 15(2), 565-579. https://doi.org/10.1007/s12559-022-10061-z
• Xuan, W., Jian-She, G., Bo-Jie, H., Zong-Shan, W., Hong-Wei, D., & Jie, W., 2022. A lightweight modified YOLOX network using coordinate attention mechanism for PCB surface defect detection. IEEE sensors journal, 22(21), 20910-20920. https://doi.org/10.1109/JSEN.2022.3208580 Zhang, Q., & Liu, H., 2021. Multi-scale defect detection of printed circuit board based on feature pyramid network, 31, 1, 76-87. http://dx.doi.org/10.1109/MMUL.2024.3359267
• Zhang, Y., Xie, F., Huang, L., Shi, J., Yang, J., & Li, Z., 2021. A lightweight one-stage defect detection network for small object based on dual attention mechanism and PAFPN. Frontiers in Physics, 9, 708097. http://dx.doi.org/10.3389/fphy.2021.708097
• Budak,İ. Gerçek Zamanlı PCB Kusur Tespiti [Video dosyası]. https://drive.google.com/drive/folders/1fS9EMJAtJaci67d6lKK-qT6VJc5-4Vj_?usp=sharing (25.11. 2024)
• Make Sense, https://www.makesense.ai/, (10.08. 2024)
• Labelbox, https://labelbox.com/, (10.08. 2024)
• LabelImg, https://medium.com/@pat.x.guillen/setting-up-labelimg-1ad1887d91c5, (10.08. 2024)
• Labelme, https://github.com/labelmeai/labelme, (10.08. 2024)
• Roboflow, https://roboflow.com/, (10.08. 2024)
• SuperAnnotate, https://superannotate.medium.com/introduction-to-object-detection-with-deep-learning-f4d2b9f4d1b5, (10.08. 2024)
• Supervisely, https://supervisely.com/labeling-toolbox/images/, (10.08. 2024)