Hybrid inspection of printed board defects
https://doi.org/10.37661/1816-0301-2024-21-3-63-79
Abstract
Objectives. A hybrid approach to the problem of searching and classifying defects in printed circuit boards (PCB) is proposed. Key factors and trends in the design and production of PCBs are considered. The relevance of the study is determined by the use of new materials and production technologies.
Methods. A hybrid approach based on the algorithm of comparison with reference and the use of the YOLO family of neural network models for detecting objects is used to solve the problem.
Results. Models were trained on public sets of PCB images with six classes of defects, and their accuracy was assessed using generally accepted metrics.
Conclusion. Experiments have shown that the YOLOv8 neural network architecture has high accuracy of defect detection, low sensitivity to image quality, presence of text and graphic objects on the PCB, but the low quality of training datasets imposes restrictions on the use of only neural networks for defect detection. It is proposed to use a hybrid approach to improve the quality of defect inspection by applying different methods depending on the quality assessment of the analyzed images.
About the Authors
V. V. Vengerenko
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Vadim V. Vengerenko, Master, Junior Researcher of the Laboratory of System Identification
st. Surganova, 6, Minsk, 220012
A. V. Inyutin
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Alexander V. Inyutin, Head of the Laboratory of System Identification
st. Surganova, 6, Minsk, 220012
References
1. Karpov S. Precision testing of printed circuit boards. What is it? Tehnologii v jelektronnoj promyshlennosti [Technologies in the Electronics Industry], 2008, no. 7, рр. 37–40 (In Russ.).
2. Cacciola M., Megali G., Pellicanó D., Morabito F. C. A GMR–ECT based embedded solution for applications on PCB inspections. Sensors and Actuators A: Physical, 2011, vol. 167, iss. 1, рр. 25–33.
3. Malamas E. N., Petrakis E., Zervakis M., Petit L., Legat J. A survey on industrial vision systems, applications and tools. Image and Vision Computing, 2003, vol. 21, iss. 2, рр. 171–188.
4. Zhang W. Q., Li A. D., Ma G. B., Yin K. B., Xia Y. D., …, Yee K. W. Interpretation of texture changes during self-annealing of electroplated copper. Microelectronic Engineering, 2010, vol. 87, iss. 12, рр. 2488–2494.
5. Lehmann D. K. X-ray systems for optimizing PCB inspection: x-ray systems are not all equal, and their differences affect the type of defects that can be detected. Circuits Assembly, 2002, vol. 13, iss. 2, рр. 35–40.
6. Levdanskij A. Optical and X-ray inspection of printed circuit boards using one system. Tehnologii v jelektronnoj promyshlennosti [Technologies in the Electronics Industry], 2005, no. 6, рр. 52–54 (In Russ.).
7. Ebayyeh A. A. R. Abu, Mousavi A. A review and analysis of automatic optical inspection and quality monitoring methods in electronics industry. IEEE Access, 2020, vol. 8, рр. 183192–183271.
8. Dudkin A. A., Inyutin A. V. Techniques for detecting defects and checking design standards on the image of printed circuit board layers. Iskusstvennyj intellekt [Artificial Intelligence], 2006, no. 3, рр. 584–591 (In Russ.).
9. Amjoud A. B., Amrouch M. Object detection using deep learning, CNNs and vision transformers: A review. IEEE Access, 2023, vol. 11, рр. 35479–35516.
Review
For citations:
Vengerenko V.V., Inyutin A.V. Hybrid inspection of printed board defects. Informatics. 2024;21(3):63-79. (In Russ.) https://doi.org/10.37661/1816-0301-2024-21-3-63-79
Views:
364
Email this article 