Journals →  Chernye Metally →  2021 →  #9 →  Back

Machine-building technologies
ArticleName Application of digital twins at the life cycle stages of special purpose products
DOI 10.17580/chm.2021.09.11
ArticleAuthor O. V. Pantyukhin, S. A. Vasin

Tula State University (Tula, Russia):

O. V. Pantyukhin, Cand. Eng., Associate Prof., Dept. of Technological systems of food, printing and packaging industries, e-mail:
S. A. Vasin, Dr. Eng., Prof., Dept. of Design., e-mail:


The selection of tools for creating digital doubles for the development, manufacture and operation of cartridge casings of sports and hunting caliber 7.62 x 39 mm was carried out. At the development stage, the computer program calculates the technological process of the sleeve manufacturing according to a given algorithm. At the manufacturing stage, with the help of modern inspection machines, it monitors and measures the geometric parameters of the quality of the semi-finished sleeve at each technological operation. The measured values are numerically transmitted to a personal computer for analysis and processing. Data processing is carried out using the method of artificial neural networks, embedded in one of the modules of the statistical program. In the program, using previously trained INS, the predicted values of quality parameters are obtained for the subsequent operation. Based on the forecast values, if necessary, a management decision is made on the impact on the process, equipment adjustment, and tool replacement. To check the sleeve at the stage of the sleeve operation, a digital double of the sleeve was created based on the finite element method relations for the elastic-plastic reinforcing material. The digital double allows you to identify the distribution of stresses and deformations in the shell when it is loaded with pressure before conducting full-scale tests.

keywords Digital twin, quality control, artificial neural network, mathematical model, digital twin structure, product quality, hardness, product life cycle

1. Pantyukhin О. V., Vasin S. А. Digital twins of the technological process for manufacturing special purpose products. Stankoinstrument. 2021. No. 1. pp. 56–58.
2. Quality management in the era of digital transformation - in the view of Russian and foreign experts. Available at:
3. Digital twin: experimenting with the future. Available at:
4. Abdrakhmanova G. I., Vishnevskiy К. О., Gokhberg L. М. et. al. What is the digital economy? Trends, competencies, measurement. Proceedings of the XX International. scientific conference “Digitalization of the economy and public administration: trends, effects, risks, resources” (April 9-12, 2019, Moscow). Moscow: Izdatelskiy dom Vysshey shkoly ekonomiki, 2019.
5. Madni A. M., Madni C. C., Lucero S. D. Leveraging digital twin technology in model-based systems engineering. Systems. 2019. Vol. 7. No. 7, Iss. 1. 13 p.
6. Frolov D. How machine learning empowers models for digital twin. Benchmark. 2018. pp. 48–53.
7. Qia Q., Taoa F., Zuoa Y., Zhaob D. Digital twin service towards smart manufacturing. Proc. CIRP. 2018. Vol. 72. pp. 237–242.
8. Lyalin V. М., Pantyukhin О. V. Experimental study of bilateral semi-hot extrusion from wire billets. Part 2. Izvestiya Tulskogo gosudarstvennogo universiteta. Seriya Tekhnicheskie nauki. 2013. pp. 246–251.
9. Danilin G. А. Ogorodnikov V. P., Zavolokin А. B. Basics of designing cartridges for small arms: textbook, 2nd edition revised and extended. Saint-Petersburg: Bryanskiy gosudarstvenny tekhnicheskiy universitet, 2010. 368 p.
10. Dudarov S. P., Papaev P. L. Theoretical foundations and practical application of artificial neural networks: textbook. Moscow: Rossiyskiy khimiko-tekhnologicheskiy universitet imeni D. I. Mendeleeva, 2014. 103 p.
11. Pavlova А. I. Information technology: the main expressions of the theory of artificial neural networks: textbook. Novosibirsk: Novosiberskiy gosudarstvenny universitet ekonomiki i upravleniya. 2017. 189 p.
12. Tsurikov А. N. Theory and practice of development of methods, algorithms and devices for training of artificial neural networks: monograph. Rostov-on-Don: FGBOU VO Rostovskiy gosudarstvenny universitet putey soobshcheniya, 2019. 183 p.
13. Fedorova N. N., Valger S. А., Danilov М. N., Zakharova Yu. V. Basics of working in ANSYS 17. Moscow: DMK Press, 2017. 209 p.
14. Pantyukhin О. V., Lyalin V. М., Kuzin V. F., Fan N. Т. Stress-strain state of a cartridge under its load by internal pressure. Izvestiya Tulskogo gosudarstvennogo universiteta. Seriya Tekhnicheskie nauki. 2013. Iss. 7. Part 2. pp. 252–262.

Language of full-text russian
Full content Buy