student
Moscow, Moscow, Russian Federation
student from 01.01.2024 until now
Almetyevsk, Kazan, Russian Federation
employee from 01.01.2023 to 01.01.2025
Moscow, Moscow, Russian Federation
004.032.26
This study focuses on the development of a model based on the YOLOv8x neural network for the automated detection of defects in printed circuit boards (PCBs). Purpose: to train a neural network capable of effectively detecting and classifying various types of PCB defects. Methods: a deep learning method based on the YOLOv8x architecture, designed for object detection tasks. An accuracy and loss metrics analysis was conducted to assess the model’s effectiveness. Results: the trained model demonstrates high accuracy in classifying defects such as missing holes, shorts, and spurious copper, achieving an accuracy of 1.0. The “open circuits” and “copper spurs” classes also yield satisfactory results. However, the “mouse bites” class requires further improvement. Practical significance: the potential application of the developed model for automating quality control processes in PCBs could significantly enhance the reliability of electronic devices and reduce the potential failures in critical systems.
printed circuit board, defects, neural network classification, YOLOv8x neural network model
1. Danilova E.A. Classification of defects in printed circuit boards. Trudy Mezhdunarodnogo simpoziuma "Nadezhnost' i kachestvo" [Proceedings of the International Symposium on Reliability and Quality]. 2013. Vol. 1. pp. 325-328. (In Russian).
2. Danilova E.A., Kochegarov I.I., Trusov V.A. Models of technological defects in the conductive pattern of printed circuit boards. Nadezhnost' i kachestvo slozhnykh sistem [Reliability and Quality of Complex Systems]. 2017. No. 2 (18). pp. 68-76. (In Russian).
3. Skladnova M.S. Methods of control for printed circuit boards. Colloquium journal. Golopristanskii gorodskoi tsentr zaniatosti [Colloquium Journal. Holoprystansk City Employment Center]. 2019. No. 25 (49). pp. 45-46. (In Russian).
4. Ksenofontov V.V. Neural networks. Problemy nauki [Problems of Science]. 2020. No. 11. p. 59. (In Russian).
5. Smith R.G., Eckroth J. Building AI applications: Yesterday, today, and tomorrow. AI Magazine. 2017. Vol. 38. No. 1. pp. 6-22.
6. Yagci B.E., Demirsoy G., Akpolat A.N. General overview of artificial neural network applications in renewable energy systems. Turkish Journal of Electromechanics and Energy. 2024. Vol. 9. No. 3. pp. 95-107.
7. Alexeeva N.S. [Face recognition from photographs using neural networks]. Mezhdunarodnyi studencheskii nauchnyi vestnik [International Student Scientific Bulletin]. 2021. No. 1. p. 55. – EDN XOMDNZ (In Russian).
8. Sharipova D.D. [ImageAI neural network: object recognition]. Informatsionnye tekhnologii: problemy i resheniya [Information Technologies: Problems and Solutions]. 2020. No. 2 (11). pp. 140-144. – EDN MQPHIN (In Russian).
9. Bondarenko V.I., Nestrugina E.S. [Criminal face recognition system using video surveillance cameras]. Donetskie chteniya 2022: obrazovanie, nauka, innovatsii, kul'tura i vyzovy sovremennosti [Donetsk Readings 2022: Education, Science, Innovations, Culture and Modern Challenges]: Materialy VII Mezhdunarodnoi nauchnoi konferentsii, posvyashchennoi 85-letiyu Donetskogo natsional'nogo universiteta, Donetsk, 27–28 oktyabrya 2022 goda / Pod obshchei redaktsiei S.V. Bespalovoi. Donetsk: Donetskii natsional'nyi universitet, 2022, pp. 236-237. – EDN RZOVEF (In Russian).
10. Bolikov S.S. [Machine vision and neural networks]. Konkurentosposobnost' territorii: Materialy XX Vserossiiskogo ekonomicheskogo foruma molodykh uchenykh i studentov, Ekaterinburg, 27–28 aprelya 2017 goda / Ekaterinburg: Ural'skii gosudarstvennyi ekonomicheskii universitet, 2017, pp. 21-22. – EDN UPJUDM (In Russian).
11. Vaishya R., et al. Artificial Intelligence (AI) applications for COVID-19 pandemic. Diabetes Metabolic Syndrome: Clinical Research Reviews. 2020. Vol. 14. No. 4. pp. 337-339.
12. Mohamed Y.A., et al. The impact of artificial intelligence on language translation: a review. IEEE Access. 2024. Vol. 12. pp. 25553-25579.
13. Muratova U.D. [Study of neural networks for chatbots]. Sbornik trudov IX Kongressa molodykh uchenykh, Sankt-Peterburg, 15–18 aprelya 2020 goda, Tom 1 / Universitet ITMO, Sankt-Peterburg: federal'noe gosudarstvennoe avtonomnoe obrazovatel'noe uchrezhdenie vysshego obrazovaniya "Natsional'nyi issledovatelskii universitet ITMO", 2021, pp. 92-95. – EDN LFVHWN (In Russian).
14. Kravchenko D.Yu., Kravchenko Yu.A., Mansur A., [et al.] [Keyword extraction optimization algorithm based on linguistic parser application]. Informatika i avtomatizatsiya [Informatics and Automation]. 2024. Vol. 23, No. 2. pp. 467-494. – DOIhttps://doi.org/10.15622/ia.23.2.6 – EDN CUIVBO (In Russian).
15. Li X. et al. Artificial intelligence applications in finance: a survey //Journal of Management Analytics. 2023. T. 10. № 4. pp. 676-692.
16. Joshi N., Dave T. Improved accuracy for heart disease diagnosis using machine learning techniques //Journal of Informatics and Web Engineering2025. T. 4. № 1. pp. 42-52.
17. Datilo P.M., Ismail Z., Dare J. A review of epidemic forecasting using artificial neural networks //Epidemiology and Health System Journal. 2019. T. 6. № 3. pp. 132-143.
18. Atan O., Jordon J., Van der Schaar M. Deep-treat: Learning optimal personalized treatments from observational data using neural networks //Proceedings of the AAAI Conference on Artificial Intelligence. 2018. T. 32. № 1.
19. Li C. et al. Deep neural network provides personalized treatment recommendations for de novo metastatic breast cancer patients //Journal of Cancer. 2024. T. 15. № 20. pp. 6668.
20. Widayani A. et al. Review of Application YOLOv8 in Medical Imaging // Physics Letters. 2024. T. 5. № 1.
21. Mumali F. Artificial neural network-based decision support systems in manufacturing processes: A systematic literature review // Computers & Industrial Engineering. 2022. T. 165. p. 107964.
22. Ribeiro J. et al. Robotic process automation and artificial intelligence in industry 4.0–a literature review //Procedia Computer Science. 2021. T. 181. pp. 51-58.
23. Edelev D.A., Blagoveshchenskaya M.M., Blagoveshchenskiy I.G. [Using neural networks as a factor in improving the quality and safety of food production in automation tasks]. Avtomatizatsiya Tekhnologicheskikh i Biznes-Protsessov – Automation of Technological and Business Processes. 2015. № 7, Iss. 1. pp. 7-10. (In Russian).
24. PCB Defects. URL: https://www.kaggle.com/datasets/akhatova/pcb-defects (accessed 17.01.2025).
25. Cheremisina O.N. [Improving the accuracy of image recognition by selecting the parameters of a convolutional neural network]. Evraziiskoe Nauchnoye Ob"edinenie – Eurasian Scientific Union. 2019. № 6-2(52). pp. 114-118. (In Russian).
26. Sirisha U. et al. Statistical analysis of design aspects of various YOLO-based deep learning models for object detection // International Journal of Computational Intelligence Systems. 2023. T. 16. № 1. p. 126.
27. Ultralytics [YOLO: Object Detection System]. URL: https://www.ultralytics.com/ru/yolo (accessed 17.01.2025). (In Russian)
28. Redmon J. et al. You only look once: Unified, real-time object detection // Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, pp. 779-788.
29. Google Colab. URL: https://colab.google/ (accessed 17.01.2025).
30. Ultralytics [F1-score]. URL: https://www.ultralytics.com/ru/glossary/f1-score (accessed 17.01.2025). (In Russian).
