Применение технологической модели детали в условиях единичного и мелкосерийного производства

D A Devyatov

doi:10.22213/2410-9304-2025-4-16-21

Authors

D. A. Devyatov Kalashnikov Izhevsk State Technical University

DOI:

https://doi.org/10.22213/2410-9304-2025-4-16-21

Keywords:

automation of production, single and small-batch production, 2D drawings, graph method, machine learning, process optimization, recognition of structural elements

Abstract

The issues ofpre-production engineering automation, especially in single and small-batch production, remain highly relevant. Modernknowledgebase software toolscombined with actively developing artificial intelligence methods, including neural networks, creates the potential for the formation and development of fully autonomous automated design systems. Automatic reading graphic and text data from 2D drawings remains one of the key tasks of pre-production engineering automation. For single and small-batch production rapid introduction of new products is a critical factor, the relevance of using the technological model of apart (TMP) increases due to the need for rapid technological processadaptation. In this paper, TMP is presented as a formalized description of the geometric, structural, and technological characteristics of a product adapted to work with 2D drawings. The structured TMP includes blocks for data input, preprocessing, hierarchical structure formation, integration with technological data, analysis and optimization, as well as output of results. Using exclusively 2D drawings minimizes the time required to introduce new products, providing accuracy and adaptability to specific requirements. The paper proposesthe approach to pre-production engineering automation based on TMP and the graph method of searching for structural elements, demonstrating significant potential for improving production efficiency. The developed software system integrating graph analysis with optical character recognition technologies, successfully recognizes elements such as the central hole of a ring-type part and generates structured parameters ready for integration into automated production management systems.

Author Biography

D. A. Devyatov, Kalashnikov Izhevsk State Technical University

Post-graduate

References

Девятов Д. А., Чернова А. А. Оценка возможности автоматизации формирования технологических процессов в мелкосерийном производстве // Вестник ИжГТУ имени М. Т. Калашникова. 2023. Т. 26, № 3. С. 67-74.

Рупинец И. С. Автоматизация управления технологическими потоками в мелкосерийном и единичном машиностроительном производстве // Инновации. Наука. Образование. 2021. № 35. С. 756-764.

Малкина И. В. Автоматизация контроля качества геометрических параметров деталей в машиностроении // Известия Самарского научного центра Российской академии наук. 2022. Т. 24, № 3 (107). С. 34-41. DOI 10.37313/1990-5378-2022-24-3-34-41.

Гатавлин Э. Г., Усманов У. К. Инновации в технологии машиностроения: современные подходы к автоматизации производственных процессов // Профессиональные коммуникации в научной среде - фактор обеспечения качества исследований. СПб.: Сциентиа, 2024. - С. 761-764.

Khan, M. T., etal. (2025). From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge.

Papadakis, K., Stavropoulos, P., Mourtzis, D. (2022). Knowledge-based manufacturability assessment for optimization of additive manufacturing processes based on automated feature recognition from CAD models. The International Journal of Advanced Manufacturing Technology, 122(5-6), 1567-1583.

Применение методов системного анализа и машинного обучения для автоматизации чтения чертежей / Д. А. Девятов, М. Р. Королева, М. С. Лялин [и др.] // Труды МАИ. 2025. № 142.

Wang, Y., Li, X., Zhang, J. (2024). Adaptive recognition of machining features in sheet metal parts based on a graph class-incremental learning strategy. Scientific Reports, 14, Article 61443.

Lin, Y.-H., Ting, Y., Huang, Y., Cheng, K., & Jong, W. (2023). Automatic Recognition of 2D Engineering Drawings. Encyclopedia, 3(4), 1456-1472.

Haar, C., Kim, H., Koberg, L. (2022). AI-based engineering and production drawing information extraction. Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus. Editors: K.-Y. Kim, L. Monplaisir, J. [Chapter in proceedings]. Frontiers in Manufacturing Technology.

Shuhui Ding, Zhongyuan Guo, Bin Wang, Haixia Wang, Fai Ma. MBD Based Machining Feature Recognition and Process. Machines 2022, 10(10), 906, 2022.

Кармишин А. А., Макаров В. М., Морохин П. Н. Цифровая подготовка производства в машиностроении // РИТМ машиностроения. 2022. № 2. С. 12-18.

Гнездилова В. А. Анализ методов машинного обучения для сопоставления разноязычных графов знаний // МНСК-2021. Новосибирск: Новосибирский национальный исследовательский государственный университет, 2021. С. 83.

Лыгин В. С., Сирота А. А., Головинский П. А. Регуляризация процесса обучения графовых нейронных сетей методом распространение меток // Вестник Воронежского государственного университета. Серия: Системный анализ и информационные технологии. 2024. № 3. С. 92-101.

Khan M. T., et al. (2024). Automatic Feature Recognition and Dimensional Attributes Extraction From CAD Models for Hybrid Additive-Subtractive Manufacturing.