DOI: 10.18503/1995-2732-2026-24-3-73-81
Abstract
In the modern world, various neural network models are becoming increasingly widespread and are being implemented in different areas of human activity. They are already actively used in technical sciences, particularly in mechanical engineering. This paper describes one of the promising methods for applying neural network models to image and video object classification and detection for processing engineering drawings of parts. In the future, the described method will make it possible to significantly reduce the time required to prepare technological documentation when launching parts into production, as the model will be able to perform some of the functions previously carried out by humans. The study is aimed at developing an automated method that can be applied to electronic engineering drawings of parts to determine the minimum surface roughness parameter among the surfaces produced by turning and milling operations. Several principal methods and tools have been used in the study, including methods for training neural network models capable of processing images and videos and solving object detection and classification tasks, methods for applying these models, and methods for developing computer programs in the Python programming language. As a result, a method implemented as a computer program has been developed. It enables engineering drawings of parts to be processed at high speed and the minimum surface roughness value to be determined with high accuracy, followed by recording the obtained values in a table. The developed method has significant potential for practical application due to the possibility of incorporating it into an integrated software system for automated equipment selection.
Keywords
object detection in images, neural networks, object recognition, computer vision, YOLO, turning, milling, equipment selection, surface roughness.
For citation
Kuznetsov S.V., Rogovik A.A. Determination of the Minimum Surface Roughness Parameter Value in Engineering Drawings of Parts Among Surfaces Produced by Turning and Milling Using Neural Network Models. Vestnik Magnitogorskogo Gosudarstvennogo Tekhnicheskogo Universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2026, vol. 24, no. 3, pp. 73-81. https://doi.org/10.18503/1995-2732-2026-24-2-73-81
1. Stepanov D.V., Makarov A.V., Molotov A.M., Obletov E.N. Convolutional neural networks for detecting defects and damage in structures. Promyshlennoe i grazhdanskoe stroitelstvo [Industrial and Civil Engineering]. 2024;(9):52-58. (In Russ.)
2. Altunina K.A., Sokolova M.V. Application of neural networks for modeling the turning process. Vestnik TGTU [Vestnik of TSTU]. 2016;22(1):122-133. (In Russ.)
3. Suzdaleva N.N. Potential for the use of neural networks by industrial enterprises under Russian conditions. Regionalnaya i otraslevaya ekonomika [Regional and sectoral economics]. 2022;(11(173)):91-94. (In Russ.)
4. Veretelnikov A.S., Gavlitskiy A.I. Application of artificial intelligence in the metalworking industry. Elektronnyy nauchnyy zhurnal «Dnevnik nauki» [Electronic scientific journal “Diary of Science”]. 2022;(12). (In Russ.)
5. Alkhanov A.A. Machine learning and its application in the modern world. Problemy nauki [Problems of science]. 2021;(7(66)):25-27. (In Russ.)
6. Redmon J., Farhadi A. YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, pp. 7263-7271.
7. Redmon J., Shooji F., Farhadi A. YOLOv5 Training and Improving Object Detectors and Segmentation Models with One Click. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2022, pp. 962-972.
8. Lin T.-Y., Dollár P., Girshick R., He K., Hariharan B., Belongie S. Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, pp. 936-944.
9. Kuznetsov S.V., Rogovik A.A., Kuznetsova E.S. Detection of parts produced by turning using the YOLOv5 object recognition model. Vestnik Magnitogorskogo gosudarstvennogo tekhnicheskogo universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2025;23(3):122-128. (In Russ.) DOI: 10.18503/1995-2732-2025-23-3-122-128.
10. Bochkovskiy A., Wang C. YOLOv5: Creating State-of-the-Art Object Detectors in Real Time. [S. l.]. ArXiv. 2021;214-219.
11. Bochkovskiy A. YOLOv7: Trainable Boosted Data-Driven Layer for Real-Time Object Detection. [S. l.]. ArXiv. 2023;5147-5155.
12. Kuznetsov S.V., Rogovik A.A. Automated determination of the maximum diameter of rotational parts in engineering drawings. Vestnik IzhGTU imeni M.T. Kalashnikova [Bulletin of Kalashnikov Izhevsk State Technical University]. 2025;28(4):29-35. (In Russ.) DOI: 10.22213/2413-1172-2025-4-29-35.
13. Kuznetsov S.V., Rogovik A.A. Automated detection and recognition of the lengths of rotational parts in engineering drawings using computer vision tools. Vestnik Magnitogorskogo gosudarstvennogo tekhnicheskogo universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2026;24(1):133-141. (In Russ.) DOI: 10.18503/1995-2732-2026-24-1-133-141.
14. Mitrofanov S.P. Nauchnaya organizatsiya mashinostroitelnogo proizvodstva [Scientific organization of machine-building production]. Leningrad: Mashinostroenie, 1976, 712 p. (In Russ.)
15. Kuznetsov S.V., Rogovik A.A. Grouping of disk-type rotational parts and similar parts when planning their manufacture in order to increase production series. Vestnik IzhGTU imeni M.T. Kalashnikova [Bulletin of Kalashnikov Izhevsk State Technical University]. 2025;28(1):24-32. (In Russ.) DOI: 10.22213/2413-1172-2025-1-24-32.