EVALUATION OF THE POSSIBILITIES OF USING NEURAL NETWORK MODELS TO OPTIMIZING REINFORCING STEEL COOLING TECHNOLOGY

V. S. Solod, V. M. Zuyev, S. B. Ivanova

About the authors

V. S. Solod, V. M. Zuyev, S. B. Ivanova

Солод Владимир Сергеевич – научный сотрудник, Федеральное государствен- ное бюджетное научное учреждение «Институт проблем искусственного интеллекта». Область научных интересов: компьютерное моделирование технологии прокатного производства, адрес:283048, г. Донецк, ул. Артема, д. 118 б.

Зуев Владимир Михайлович – заведующий отдела Интеллектуальных робото- технических систем, Федеральное государственное бюджетное научное учреждение «Институт проблем искусственного интеллекта». Область научных интересов: компью- терное моделирование технологии прокатного производства, нейронные сети. адрес:283048, г. Донецк, ул. Артема, д. 118 б.

Иванова Светлана Борисовна – директор Федерального государственного бюджетного научного учреждения «Институт проблем искусственного интеллекта», г. Донецк, адрес: 283048, г. Донецк, ул. Артема, д. 118 б, Область научных интересо в: искусственный интеллект, интеллектуальные робототехнические системы.

Download PDF

UDC: 621.771.07:004.94
DOI: 10.24412/2413-7383-2025-3-38-65-77
Language: Russian

Abstract: The aim of the work is to evaluate the possibilities of using simple artificial neural networks (ANN) for modeling complex metallurgical p roduction processes. The application of ANN for describing the technology of accelerated cooling (AC) of reinforcing bars in the rolling mill flow, designed to form a specified level of mechanical properties of finished rolled products, is considered. Based on the literature analysis, a set of input and target parameters, the ANN architecture are determined. A data set for training the ANN, obtained by calculating according to the mathematical model of the authors, is developed. The training process was carried out with a variable number of neurons and target parameters. The analysis of the results of model evaluation is carried out. The direction of further research is proposed.

Keywords: reinforcement profile, accelerated cooling, perceptron, network model

References

1. Neural network modeling of the process of obtaining wide -strip hot -rolled steel with specified mechanical properties / V. M. Salganik, A. M. Pesin, S. V. Denisov [et al.] // Rolled products production. - 2008. - No. 8. - P. 26-27. - EDN JTHZKJ.
2. V. I. Gubinsky, A. A. Rybalov Modeling of accelerated cooling of reinforcing bars in the flow of continuous small-section mills. "Industrial heat engineering", 2002, v. 24, No. 6. -P. 24-28.
3. . Pilyushenko V. L. Nogovitsyn A. V. Phenomenological model of mechanical properties of rolled low -carbon microalloye d steel. / Fundamental and applied problems of ferrous metallurgy. - Kyiv: Naukova Dumka, 1995.
4. Nikolaeva S.G. Neural networks. Implementation in Matlab: tutorial / S.G. Nikolaeva. - Kazan: Kazan. state power University, 2015. - 92 p.
5. Gorban A.N. R ossiev D.A. Neural networks on a personal computer. - Novosibirsk: Nauka, 1996. - 224 p.
6. Zuev V.M. Using a neural network to control mechanisms. (lifting targets). [Abstracts of the report]. Proceedings of the Donetsk international scientific round table "Artificial Intelligence: theoretical aspects and practical application" AI -2020. – Donetsk: State University of Artificial Intelligence, 2020. – P. 73–77.
7. Zuev V. M. Using a neural network to control mechanisms. Proceedings of the conference in Divnomorsk oye 2021. All -Russian multi -conference on control problems.
8. V. M. Zuev, O. A. Butov, S. B. Ivanova, A. A. Nikitina, S. I. Ulanov. A method for training a neural network to control a robot / International Peer -Reviewed Scientific Journal “Problems of Artifi cial Intelligence”, ISSN 2413 - 7383. – 2021 – No. 2 (21). – P. 22–33.
9. Fedorov, M. V. (Corresponding Member of the Russian Academy of Sciences) New Methods of Machine Learning: Using Fundamental Knowledge to Solve Practical Problems: [online abstract report] [Electronic resource] / M. V. Fedorov // Program of the II All -Russian School -Seminar on Artificial Intelligence and Big Data in Technical, Industrial, Natural and Social Systems. - National Center for Physics and Mathematics (NCPM). - Date: November 25 -29, 2024 - (date of access: 04.04.2025).
10. Solod V. S. Physical and mathematical model for the development of an expert system for accelerated cooling of reinforcing bars / V. S. Solod / Problems of Artificial Intelligence 2025 No. 2 (37). - P. 44-58. DOI 10.34757/2413 -7383.2025-2-37-44-58
11. Heat and Mass Transfer/S.I.Ginkul, V.I.Sheludchenko, V.V.Kravtsov, S.V.Palkina. -Donetsk: Nord -Press, 2006. -298 p.
12. Morgunov K.P. Hydraulics: Textbook. - St. Petersburg: Lan Publishing House, 201 4. - 288 p.: ill.
13. Chudina, O.V. Theory and Practice of Heat Treatment of Metals: a teaching aid to a multimedia publication / O.V. Chudina, G.V. Gladova, A.V. Ostroukh. - M.: MADI, 2013. - 64 p.
14. O. Tskitishvili, A. N. Chudnovets, V. N. Brukhansky, D. P. K ukuy, V. S. Solod, A. A. Maltsev Development of high-quality production at the newest medium - and small -section mill 390 in Ukraine // JSC "Chermetinformatsiya" Bulletin "Ferrous Metallurgy". - 2011. - No. 7. - P. 56 - 65.
15. "XGBoost Documentation" / [Electr onic resource] // XGBoost Documentation: [website]. - URL: https://xgboost.readthedocs.io/en/release_3.0.0/# (accessed: 04.05.2025).
16. A. D. Smorodinov, T. V. Gavrilenko, V. A. Galkin, Theoretical foundations of artificial neural networks for solving the problem of approximation and interpolation. Advances in Cybernetics 2023;4(4):41–53 DOI: 10.51790/2712-9942-2023-4-4-04 2С Солод В. С. Зуев В. М. Иванова С. Б.
17. Sergeev, A. P. Introduction to neural network modeling: textbook / A. P. Sergeev, D. A. Tarasov; under the general editorship of A. P. Sergeev. — Ekaterinburg: Publishing house of the Ural. University, 2017. — 128 p. ISBN 978-5-7996-2124-7
18. Khlivnenko L. V. Practice of neural network modeling: a textbook for universities / L. V. Khlivnenko, F. A. Pyatakovich. - 2nd ed. reprinted. St. Petersburg: Lan, 2021. -200 p.: ill. - Text: direct. ISBN 978.5.8114.8264.1
19. Golovko, V. A. Neural network data processing technologies: a textbook / V. A. Golovko, V. V. Krasnoproshin. - Minsk: BSU, 2017. - 263 p. - ISBN 978.985.566.467.4.
20. Vichugov V.N. Modified gradient algorithm for training radial-basis neural networks. News of Tomsk

Issue: 3(38)'2025
Section: MATHEMATICAL MODELING, NUMERICAL METHODS AND SOFTWARE SYSTEMS
How to cite: V. S. Solod, V. M. Zuyev, S. B. Ivanova. EVALUATION OF THE POSSIBILITIES OF USING NEURAL NETWORK MODELS TO OPTIMIZING REINFORCING STEEL COOLING TECHNOLOGY // Problems of Artificial Intelligence. - 2025. - № 3 (38). - P. 65-77. - https://paijournal.guiaidn.ru/en/2025/3(38)-6.html

Back to issue 3(38)'2025