Deep Learning Framework for Real-Time PCB Defect Detection and Automated Segregation
Keywords:
E-waste segregation, PCB defect detection, Raspberry Pi 4, Smart manufacturing, YOLOv8Abstract
Quality control in semiconductor and Printed Circuit Board (PCB) production demands inspection methods that are fast, consistent, and capable of identifying small surface-level faults. Conventional manual checking is difficult to scale and may lead to missed defects when production volume is high. Recent research indicates that computer-vision models, particularly YOLO-based detectors, are suitable for real-time industrial inspection because they can locate and classify objects in a single processing stage. This paper reviews recent work on PCB defect detection, semiconductor inspection, and e-waste sorting, and presents a proposed system that combines YOLOv8, camera input, a Raspberry Pi 4, and a motor-driven conveyor arrangement. The review identifies three gaps in existing work: the lack of a link between detection and physical action, the limited attention to low-cost embedded deployment, and the absence of a reusability decision after defect detection. As the hardware prototype and testing phase are still in progress, the manuscript reports the review findings, system objectives, proposed workflow, expected outcomes, and implementation challenges without claiming experimental results. The proposed system classifies components as reusable or non-reusable and supports automatic segregation for smart manufacturing and e-waste handling. This is a review article with a proposed framework; reusability criteria and an evaluation plan are defined for later experimental validation.
References
A. P. Rao et al., "Hierarchical Optimization Framework for Robust PCB Defect Detection via Adaptive YOLOv12 Architecture," in IEEE Access, vol. 14, pp. 28754-28774, 2026.
W. Chen, Z. Huang, Q. Mu and Y. Sun, "PCB Defect Detection Method Based on Transformer-YOLO," in IEEE Access, vol. 10, pp. 129480-129489, 2022.
H. Ge, Y. Shi, M. Zhang, Y. Wei, H. Zhang and X. Cao, "YOLO: An Improved High-Accuracy Method for PCB Defect Detection," 2024 IEEE 12th International Conference on Computer Science and Network Technology (ICCSNT), Dalian, China, 2024, pp. 159-165.
Y. Li and W. Yang, "YOLO-DHC: A Multi-scale method for PCB defect detection," 2024 4th International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM), Chengdu, China, 2024, pp. 314-319.
C. Mo, Z. Hu, J. Wang, and X. Xiao, "SGT-YOLO: A Lightweight Method for PCB Defect Detection," in IEEE Transactions on Instrumentation and Measurement, vol. 74, pp. 1-11, 2025.
X. Zuo, N. Zhao, K. Wang, and J. Hu, “MDEB-YOLO: A Lightweight Multi-Scale Attention Network for Micro-Defect Detection on Printed Circuit Boards,” Micromachines, vol. 17, no. 2, p. 192, Jan. 2026.
G. Fontana, M. Calabrese, L. Agnusdei, G. Papadia, and A. Del Prete, “SolDef_AI: An Open Source PCB Dataset for Mask R-CNN Defect Detection in Soldering Processes of Electronic Components,” Journal of Manufacturing and Materials Processing, vol. 8, no. 3, pp. 117–117, May 2024.
R. S. Midigudla, T. Dichpally, U. Vallabhaneni, Y. Wutla, D. M. Sundaram, and S. Jayachandran, “A Comparative Analysis of Deep Learning Models for Waste Segregation: YOLOv8, EfficientDet, and Detectron 2,” Multimedia Tools and Applications, vol. 84, no. 29, pp. 35941–35964, Jan. 2025.
S. Rai, R. Chawla, M. Vashishath, and G. Fortino, “EW YOLO: Edge Computing IoT and YOLOv11 Setup for E-Waste,” Applied Sciences, vol. 16, no. 4, p. 2152, Feb. 2026.
A. Zhalgas, B. Amirgaliyev, B. Boltay, D. Shegenova, N. Zhylkybay, and D. Yedilkhan, “Development of an Intelligent Waste Segregation System Using a Self-Collected Dataset and Deep Learning Methods”, Journal of Robot Control (JRC), vol. 7, no. 1, pp. 3393–3404, Mar. 2026.
R. Khadka, P. Joshi, N. K. Kanth, and S. Gwachha, “Waste Segregation System”, International Journal on Engineering Technology, vol. 2, no. 2, pp. 36–43, May 2025.
O. Tyumentseva, K. Kamunur, L. Mussapyrova, A. Batkal, and R. Nadirov, “Selective Electrochemical Leaching of Copper From Fragmented Waste Printed Circuit Boards in an Alkaline Sulfate–Glycine Electrolyte,” Metals, vol. 16, no. 2, p. 214, Feb. 2026.
T. Zhang, Q. Yin, S. Li, T. Guo, and Z. Fan, “An Optimized Genetic Algorithm-Based Wavelet Image Fusion Technique for PCB Detection,” Applied Sciences, vol. 15, no. 6, p. 3217, Mar. 2025.
P. Chen and F. Xie, “A Machine Learning Approach for Automated Detection of Critical PCB Flaws in Optical Sensing Systems,” Photonics, vol. 10, no. 9, pp. 984–984, Aug. 2023.
X. Yin, Z. Zhao, and L. Weng, “MAS-YOLO: A Lightweight Detection Algorithm for PCB Defect Detection Based on Improved YOLOv12,” Applied Sciences, vol. 15, no. 11, pp. 6238–6238, Jun. 2025.
T. Zhang, S. Yan, and G. Qin, “Lightweight Semantic-Guided FCOS for In-Line Micro-Defect Inspection in Semiconductor Manufacturing,” Micromachines, vol. 17, no. 4, p. 473, Apr. 2026.
Z. Sun, X. Huang, B. Wei, and Y. Li, “SDD-RT-DETR: A Lightweight and Efficient Printed Circuit Board Surface Defect Detection Method Based on an Improved RT-DETR Toward Sustainable Manufacturing,” Sustainability, vol. 18, no. 5, p. 2518, Mar. 2026.
T. Zhang, J. Zhang, P. Pan, and X. Zhang, “YOLO-RRL: A Lightweight Algorithm for PCB Surface Defect Detection,” Applied Sciences, vol. 14, no. 17, p. 7460, Aug. 2024.
Y. Tang, R. Liu, and S. Wang, “YOLO-SUMAS: Improved Printed Circuit Board Defect Detection and Identification Research Based on YOLOv8,” Micromachines, vol. 16, no. 5, pp. 509–509, Apr. 2025.
