Performance Analysis of YOLO11 Models in PCB Defect Detection Tasks

Öz

Printed Circuit Board (PCB) defect detection is critical in electronics manufacturing, as undetected faults can lead to severe quality control issues. Recent advancements in deep learning, particularly object detection models, have significantly improved inspection systems' accuracy and speed. This study explores the performance of the YOLO11 (You Only Look Once version 11) object detection architecture on a multi-class PCB defect dataset. Five YOLO11 variants—YOLO11n, YOLO11s, YOLO11m, YOLO11l, and YOLO11x—were trained and evaluated under identical conditions using high-resolution images containing six defect types. Metrics such as mAP@50, mAP@50-95, and FPS were used for evaluation. Results demonstrate that YOLO11l achieved the highest mAP@50-95 of 0.551, while YOLO11n achieved up to 166 Frame Per Second (FPS) on an NVIDIA A100 GPU, confirming its real-time capability. Comparative analysis against state-of-the-art models confirms that YOLO11 variants offer an effective trade-off between accuracy and efficiency. This study positions YOLO11 as a strong candidate for real-time PCB inspection systems.

Anahtar Kelimeler

• PCB Defect Detection
• Deep Learning
• YOLO11

PCB Hata Tespit Görevlerinde YOLO11 Modellerinin Performans Analizi

Öz

Baskılı Devre Kartı (PCB) hata tespiti, elektronik üretiminde kritik bir süreçtir; tespit edilemeyen hatalar ciddi kalite kontrol problemlerine yol açabilir. Derin öğrenme ve özellikle nesne tespiti modellerindeki son gelişmeler, denetim sistemlerinin doğruluk ve hızında önemli iyileştirmeler sağlamıştır. Bu çalışma, çok sınıflı bir PCB arıza tespit veri kümesi üzerinde YOLO11 (You Only Look Once versiyon 11) nesne tespiti mimarisinin performansını incelemektedir. YOLO11 ailesine ait beş farklı varyant—YOLO11n, YOLO11s, YOLO11m, YOLO11l ve YOLO11x—altı farklı arıza türü içeren yüksek çözünürlüklü görüntüler kullanılarak, aynı eğitim koşulları altında değerlendirilmiştir. Değerlendirme için mAP@50, mAP@50-95 ve FPS gibi metrikler kullanılmıştır. Sonuçlar, YOLO11l modelinin 0.551 mAP@50-95 ile en yüksek doğruluk değerine ulaştığını, YOLO11n modelinin ise NVIDIA A100 GPU üzerinde saniyede 166 kareye (FPS) kadar gerçek zamanlı performans sergilediğini göstermektedir. Yapılan karşılaştırmalar, YOLO11 ailesinin doğruluk ve verimlilik arasında etkili bir denge sunduğunu doğrulamaktadır. Bu çalışma, YOLO11 mimarisinin gerçek zamanlı PCB denetim sistemleri için güçlü bir aday olduğunu ortaya koymaktadır.

Anahtar Kelimeler

• PCB Hata Tespiti
• Derin Öğrenme
• YOLO11

Kaynakça

1. [1] V. K. Ancha, F. N. Sibai, V. Gonuguntla, R. Vaddi, (2024). Utilizing YOLO models for real-world scenarios: Assessing novel mixed defect detection dataset in PCBs, IEEE Access. 12, 100983–100990. https://doi.org/10.1109/ACCESS.2024.3430329.
2. [2] Q. Ling, N.A.M Isa, (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.
3. [3] K. Singh, S. Kharche, A. Chauhan, P. Salvi, (2024). PCB defect detection methods: A review of existing methods and potential enhancements, Journal of Engineering Science & Technology Review. 17(1), 156-167. https://doi.org/10.25103/jestr.171.19.
4. [4] I.-C. Chen, R.-C. Hwang, H.-C Huang, (2023). PCB defect detection based on deep learning algorithm, Processes. 11(3), 775. https://doi.org/10.3390/pr11030775.
5. [5] L. Cai, J. Li, (2022). PCB defect detection system based on image processing. Journal of Physics: Conference Series, Qingdao, China, Conf. Ser. 2383, pp. 012077. https://doi.org/10.1088/1742-6596/2383/1/012077.
6. [6] G. Zhang, Y. Cao, (2023). A novel PCB defect detection method based on digital image processing. Journal of Physics: Conference Series, Suzhou, China, Conf. Ser. 2562, pp. 012030. https://doi.org/10.1088/1742-6596/2562/1/012030.
7. [7] S. H. I. Putera, Z. Ibrahim, (2010). Printed circuit board defect detection using mathematical morphology and MATLAB image processing tools. 2nd International Conference on Education Technology and Computer, Shanghai, China, pp. 359. https://doi.org/10.1109/ICETC.2010.5530052.
8. [8] M. Baygin, M. Karakose, A. Sarimaden, E. Akin, (2017). Machine vision based defect detection approach using image processing. 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkey, pp. 1–5. https://doi.org/10.1109/IDAP.2017.8090292.

9. [9] H. Hagi, Y. Iwahori, S. Fukui, Y. Adachi, M. K. Bhuyan, (2014). Defect classification of electronic circuit board using SVM based on random sampling, Procedia Computer Science. 35, 1210–1218. https://doi.org/10.1016/j.procs.2014.08.218.
10. [10] P. P. Londe, S. A. Chavan, (2014). Automatic PCB defects detection and classification using MATLAB, International Journal of Current Engineering and Technology. 4(3), 31–36.
11. [11] E. H Yuk, S. H. Park, C.-S. Park, J.-G. Baek, (2018). Feature-learning-based printed circuit board inspection via Speeded-Up Robust Features and Random Forest, Applied Sciences. 8(6), 932. https://doi.org/10.3390/app8060932.
12. [12] Y. Li, S. Li, (2017). Defect detection of bare printed circuit boards based on gradient direction information entropy and uniform local binary patterns, Circuit World. 43(4), 145–151. https://doi.org/10.1108/CW-06-2017-0028.
13. [13] J. Niu, J. Huang, L. Cui, B. Zhang, A. Zhu, (2022). A PCB defect detection algorithm with improved Faster R-CNN. International Conference on Big Data Applications and Services Engineering (ICBASE), Guangzhou, China, pp. 283–292.
14. [14] W. Shi, Z. Lu, W. Wu, H. Liu, (2020). Single-shot detector with enriched semantics for PCB tiny defect detection, The Journal of Engineering. 2020(10), 366-372. https://doi.org/10.1049/joe.2019.1180.
15. [15] V. A Adibhatla, H.-C. Chih, C.-C. Hsu, J. Cheng, M. F. Abbod, J.-S. Shieh, (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.
16. [16] R. Khanam, M. Hussain, (2024). YOLOv11: An overview of the key architectural enhancements. arXiv. https://doi.org/10.48550/arxiv.2410.17725.
17. [17] N. Dave, V. Tambade, B. Pandhare, S. Saurav, (2016). PCB defect detection using image processing and embedded system, International Research Journal of Engineering and Technology (IRJET). 3(5), 1897–1901.
18. [18] L. Zhou, (2025). Research on PCB defect detection method based on principal component analysis. International Technology and Innovation Conference (ITOEC), Chongqing, China, pp. 1070–1074. https://doi.org/10.1109/ITOEC63606.2025.10967656.
19. [19] Y. Chang, Y. Xue, Y. Zhang, J. Sun, Z. Ji, H. Li, T. Wang, J. Zuo, (2024). PCB defect detection based on PSO-optimized threshold segmentation and SURF features, Signal, Image and Video Processing. 18, 4327–4336. https://doi.org/10.1007/s11760-024-03075-7.
20. [20] C. Zhang, W. Shi, X. Li, H. Zhang, H. Liu, (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.
21. [21] B. Hu, J. Wang, (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.
22. [22] G. Shao, Y. Zhang, T. Li, J. Wu, J. Luo, F. Gao, J. Ma, T. Liu, (2021). An improved YOLOv3 network for PCB defect detection. China Automation Congress (CAC), Beijing, China, pp. 1819–1823. https://doi.org/10.1109/CAC53003.2021.9728216.
23. [23] A. Chaudhari, V. Upganlawar, T. Barve, R. Vaidya, D. Shelke, (2024). Analysis of YOLO v3 for multiple defects detection in PCB. 2024 Parul International Conference on Engineering and Technology (PICET), Vadodara, India, pp. 1–6. https://doi.org/10.1109/PICET60765.2024.10716153.
24. [24] M. Liang, J. Wu, H. Cao, (2022). Research on PCB small target defect detection based on improved YOLOv5. 2022 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence (ICSMD), Harbin, China, pp. 1–5. https://doi.org/10.1109/ICSMD57530.2022.10058458.
25. [25] Y. Zhang, H. Zou, J. Wang, Z. Lei, M. Zhou, (2023). Lightweight neural network-based real-time PCB defect detection system. 2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Yibin, China, pp. 1–6. https://doi.org/10.1109/SAFEPROCESS58597.2023.10295891.
26. [26] Q Li, L. Wu, H. Xiao, C. Huang, (2024). PCB-DETR: A detection network of PCB surface defect with spatial attention offset module, IEEE Access. 12, 158436–158445. https://doi.org/10.1109/ACCESS.2024.3486176.
27. [27] Y. Pan, L. Zhang, Y. Zhang, (2024). Rapid detection of PCB defects based on YOLOx-Plus and FPGA, IEEE Access. 12, 61343–61358. https://doi.org/10.1109/ACCESS.2024.3387947.
28. [28] X. Huang, W. Li, (2024). A novel PCB defect detection network based on the improved YOLOv8 with fusion of hybrid attention transformer and bidirectional feature pyramid network. 2024 4th International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC), Xiamen, China, pp. 207–211. https://doi.org/10.1109/ICAIRC64177.2024.10900305.
29. [29] X. Gu, C. Cao, Z. Xu, (2024). Research on PCB defect detection algorithm based on improved YOLOv8. 2024 6th International Conference on Frontier Technologies of Information and Computer (ICFTIC), Qingdao, China, pp. 1103–1108. https://doi.org/10.1109/ICFTIC64248.2024.10913102.
30. [30] Q. Zeng, C. Zhao, P. He, H. Gao, (2024). LSDM-PCB: A lightweight small defect detection model for printed circuit board. 2024 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, pp. 673–679 https://doi.org/10.1109/ICIP51287.2024.10647590.
31. [31] S. You, (2022). PCB defect detection based on generative adversarial network. 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China, pp. 557–560. https://doi.org/10.1109/ICCECE54139.2022.9712737.
32. [32] C. Chen, Q. Wu, J. Zhang, H. Xia, P. Lin, Y. Wang, M. Tian, R. Song, (2024). U2D2PCB: Uncertainty-aware unsupervised defect detection on PCB images using reconstructive and discriminative models, IEEE Transactions on Instrumentation and Measurement. 73, 1-10. https://doi.org/10.1109/TIM.2024.3386210.
33. [33] D. Lang, Z. Lv, (2025). SEPDNet: Simple and effective PCB surface defect detection method, Scientific Reports. 15, 10919. https://doi.org/10.1038/s41598-024-84859-2.
34. [34] L. Zhu, R. Zhao, (2025). A novel PCB surface defect detection method based on separated global context attention to guide residual context aggregation, Scientific Reports. 15, 9620. https://doi.org/10.1038/s41598-024-84961-5.
35. [35] X. Zhao, H. Zhang, C. Song, H. Li., H. Guo, (2025). Lightweight intelligent detection algorithm for surface defects in printed circuit board, Computers & Industrial Engineering. 203, 111030. https://doi.org/10.1016/j.cie.2025.111030.
36. [36] W. Shi, Z. Lu, W. Wu, H. Liu, (2020). Single-shot detector with enriched semantics for PCB tiny defect detection, The Journal of Engineering. 2020(3), 366–372. https://doi.org/10.1049/joe.2019.1180.
37. [37] L. Kang, Y. Ge, H. Huang, M. Zhao, (2022). Research on PCB defect detection based on SSD. 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China, pp. 1315–1319. https://doi.org/10.1109/ICCASIT55263.2022.9986754.
38. [38] K. P. Anoop, N. S. Sarath, V. V. Kumar, (2015). A review of PCB defect detection using image processing, International Journal of Engineering and Innovative Technology (IJEIT). 4(11), 188–192.
39. [39] Q. Ling, N. A. M. Isa, (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.
40. [40] W. Huang, P. Wei, (2019). A PCB Dataset for Defects Detection and Classification. arXiv. 10.48550/arXiv.1901.08204.
41. [41] W. Zhu, X. Han, K. Zhang, S. Lin, J. Jin, (2025). Application of YOLO11 model with spatial pyramid dilation convolution (SPD-Conv) and effective squeeze-excitation (EffectiveSE) fusion in rail track defect detection, Sensors. 25(8), 2371. https://doi.org/10.3390/s25082371.
42. [42] P. Hidayatullah, N. Syakrani, M. R. Sholahuddin, T. Gelar, R. Tubagus, (2025). YOLOv8 to YOLO11: A comprehensive architecture in-depth comparative review. arXiv. https://doi.org/10.48550/arXiv.2501.13400.
43. [43] N. Jegham, C. Y. Koh, M. Abdelatti, A. Hendawi, (2025). YOLO evolution: A comprehensive benchmark and architectural review of YOLOv12, YOLO11, and their previous versions. arXiv. https://doi.org/10.48550/arXiv.2411.00201
44. [44] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, D. Ren, (2020). Distance-IoU loss: Faster and better learning for bounding box regression. AAAI Conference on Artificial Intelligence, New York, USA, 34(07), pp. 12993–13000. https://doi.org/10.1609/aaai.v34i07.6999.
45. [45] G. Jocher, J. Qiu, A. Chaurasia, (2023). Ultralytics YOLO (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics.
46. [46] L. Rampini, F. R. Cecconi, (2024). Synthetic images generation for semantic understanding in facility management, Construction Innovation. 24(1), 33–48. https://doi.org/10.1108/CI-09-2022-0232.
47. [47] I. Dedovic, (2017). Efficient probability distribution function estimation for energy based image segmentation methods (Doctoral Thesis). RWTH Aachen University, Germany https://doi.org/10.18154/RWTH-2016-10831.
48. [48] J. Tang, S. Liu, D. Zhao, L. Tang, W. Zou, B. Zheng, (2023). PCB-YOLO: An improved detection algorithm of PCB surface defects based on YOLOv5, Sustainability. 15(7), 5963. https://doi.org/10.3390/su15075963.
49. [49] Y. Pan, L. Zhang Y. Zhang, (2024). Rapid detection of PCB defects based on YOLOx-Plus and FPGA, IEEE Access. 12, 61343–61358. https://doi.org/10.1109/ACCESS.2024.3387947.
50. [50] J. An, Z. Shi, (2024). YOLOv8n-enhanced PCB defect detection: A lightweight method integrating spatial–channel reconstruction and adaptive feature selection, Applied Sciences. 14(17), 7686. https://doi.org/10.3390/app14177686.
51. [51] G. Xiao, S. Hou, H. Zhou, (2024). PCB defect detection algorithm based on CDI-YOLO, Scientific Reports. 14, 7351. https://doi.org/10.1038/s41598-024-57491-3.
52. [52] C. Liu, X. Zhou, J. Li, C. Ran, (2023). PCB board defect detection method based on improved YOLOv8, Frontiers in Computing and Intelligent Systems. 6(2), 1–6. https://doi.org/10.54097/fcis.v6i2.01.
53. [53] H. Guo, H. Zhao, Y. Zhao, W. Liu, (2024). PCB defect detection algorithm based on deep learning, Optik. 315, 172036. https://doi.org/10.1016/j.ijleo.2024.172036.
54. [54] W.Chen, Z. Huang, Q. Mu, Y. Sun, (2022). PCB defect detection method based on Transformer-YOLO, IEEE Access. 10, 129480–129489. https://doi.org/10.1109/ACCESS.2022.3228206.