PCB Solder Defect Detection Using Machine Learning
Author(s): 1. Dr. Sandhya Shinde, 2. Prem Ghodekar, 3. Sarvesh Kolwadkar, 4. Vedant Tekale
Authors Affiliations:
- Assistant Professor, Department of Semiconductor Engineering, Dr.D.Y.Patil International University, Akurdi, Maharashtra, India
- Student, Electronics and Telecommunications Engineering, Dr.D.Y.Patil Institute of Engineering Management and Research, Akurdi, Maharashtra, India
- Student, Electronics and Telecommunications Engineering, Dr.D.Y.Patil Institute of Engineering Management and Research, Akurdi, Maharashtra, India
- Student, Electronics and Telecommunications Engineering, Dr.D.Y.Patil Institute of Engineering Management and Research, Akurdi, Maharashtra, India
Printed Circuit Boards (PCBs) serve as the foundation of nearly all modern electronic systems, where minor defects can lead to complete device malfunction. Therefore, ensuring accurate and efficient inspection is essential. Conventional inspection methods, including manual visual checking and Automated Optical Inspection (AOI), often fall short when it comes to precision, especially in detecting minute or concealed flaws. To address these limitations, this project presents an automated PCB defect detection framework powered by deep learning and computer vision techniques. In this study, we utilized the Mixed PCB Defect Dataset from Mendeley, which contains real-world samples with various defect types such as open circuits, short circuits, mouse bites, spurious copper, pinholes, and defect-free boards for reference. The images were preprocessed using OpenCV to enhance visibility and uniformity of key features before training. A YOLOv8 object detection model was then employed to simultaneously identify multiple defects with high accuracy and real-time efficiency. The developed system enables users to simply upload a PCB image, after which the trained model automatically detects and marks defective areas with bounding boxes and confidence scores. Designed for accessibility, the system can be extended to operate with standard mobile or USB cameras, offering a cost-effective and practical solution for industrial quality control. This approach not only accelerates inspection but also improves consistency and reliability, contributing to the advancement of intelligent and automated manufacturing.
Dr Sandhya Shinde, Prem Ghodekar, Vedant Tekale, Sarvesh Kolwadkar (2026); PCB Solder Defect Detection Using Machine Learning, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-12, Issue-2, Available on – https://www.ijirmf.com/
1. F. Fan, B. Wang, G. Zhu, and J. Wu, “Efficient Faster R-CNN: Used in PCB Solder Joint Defects and Components Detection,” IEEE 4th Int. Conf. on Computer and Communication Engineering Technology (CCET), pp. 20–24, 2021
2. Z. Zhang, H. Wang, S. Zhou, R. Zhou, and L. Sun, “A Cascaded Zoom-In Method for Defect Detection of Solder Joints,” Proc. ICSP 2018, pp. 1081–1086, 2018.
3. M.-L. Tham, B. Y. Chong, Y. H. Tan, Y. K. Wong, S. L. Chean, and W. K. Tan, “Optimizing Deep Learning Inference to Detect PCB Soldering Defects,” IEEE Int. Conf. on Artificial Intelligence in Engineering and Technology (IICAIET), 2022.
4. Q. Ling and N. A. M. Isa, “Printed Circuit Board Defect Detection Methods Based on Image Processing, Machine Learning and Deep Learning: A Survey,” IEEE Access, vol. 11, pp. 15921–15950, 2023.
5. S. Gao, H. Zhang, and H. Mi, “Solder Joint Defect Detection Based on Image Segmentation and Deep Learning,” IEEE Conf. on Industrial Informatics, 2019.
6. P. Selvam et al., “YOLO-DefXpert: An Advanced Defect Detection on PCB Surfaces Using Improved YOLOv11 Algorithm,” IEEE Access, vol. 13, pp. 143085–143101, Aug. 2025.
7. W. Zhang, Y. Lu, T. Chen, and J. Li, “A Random Forest Algorithm for PCB SMD Defect Detection,” IEEE Trans. on Components, Packaging and Manufacturing Technology, vol. 15, no. 5, pp. 1135–1143, May 2025.
8. S. T. Subbulakshmi, R. Madhavan, V. Ramachandran, M. Revathi, P. Anand, and G. H. Subramanian, “Machine Learning Models for PCB Defect Detection: A Survey,” 6th Int. Conf. on Recent Trends in Advanced Computing (ICRTAC), pp. 1–6, 2023.
9. V. Mankad, M. I. Patel, N. Bhanvadia, and R. Gajjar, “PCB Classification using Convolutional Neural Network,” 3rd Int. Conf. on Advances in Computing, Communication Control and Networking (ICACCCN), pp. 986–990, 2021.
10. A. K. Chowdhury et al., “Printed Circuit Board Surface Defect Inspection via YOLOv5 Deep Learning Algorithm,” IEEE 6th Int. Conf. in Robotics and Manufacturing Automation (ROMA), pp. 259–264, Aug. 2025.