MODELING OF DECOMPOSITION PRODUCTS OF SUPERCOOLED AUSTENITEIN PIPE STEELS USING ARTIFICIAL INTELLIGENCE METHODS

Authors

  • M. F. GAFAROV South Ural State University (National Research University), Russia, Chelyabinsk; PJSC “ТМК”, Russia, Chelyabinsk Author
  • K. YU. OKISHEV Ural Federal University named after the first President of Russia B. N. Yeltsin, Russia, Ekaterinburg Author
  • А. N. MAKOVETSKII PJSC “ТМК”, Russia, Chelyabinsk Author
  • К. P. GAFAROVA South Ural State University (National Research University), Russia, Chelyabinsk Author
  • Е. А. GAFAROVA South Ural State Humanitarian Pedagogical University, Russia, Chelyabinsk Author

DOI:

https://doi.org/10.32339/0135-5910-2024-1-38-47

Keywords:

heat treatment, modeling, machine learning

Abstract

The process of constructing machine learning models for predicting the microstructure of pipe steels after
continuous cooling is shown, including the assembly and preparation of data, the source of which are thermokinetic decay diagrams of supercooled austenite. Statistics of intermediate and final data, as well as algorithms for their transformation are presented. Estimates of machine learning models for selected microstructures are considered. A method for generating data in conditions of a small sample and the introduction of an estimated feature of grain size are proposed. Validation of the models and interpretation of the significance of the features were carried out. The practical use of models for constructing thermokinetic diagrams of austenite decay and analysis of simulation results is shown.

Author Biographies

  • M. F. GAFAROV, South Ural State University (National Research University), Russia, Chelyabinsk; PJSC “ТМК”, Russia, Chelyabinsk

    Postgraduate Student, Expert of the Competence Center for Mathematical Modeling and Data Analysis

  • K. YU. OKISHEV, Ural Federal University named after the first President of Russia B. N. Yeltsin, Russia, Ekaterinburg

    HD (Phys.-Math.), Professor of the Department of Heat Treatment and Physics of Metals

  • А. N. MAKOVETSKII, PJSC “ТМК”, Russia, Chelyabinsk

    PhD (Tech.), Head of the Department of Pipes of the Energy Complex and Special Types of Pipes

  • К. P. GAFAROVA, South Ural State University (National Research University), Russia, Chelyabinsk

    Postgraduate Student, Lecturer of the Department of Materials Science and Physical Chemistry of Materials

  • Е. А. GAFAROVA, South Ural State Humanitarian Pedagogical University, Russia, Chelyabinsk

    PhD (Pedagogy), Associate Professor of the Department of Motor Transport, Information Technology and Methods of Teaching Technical Disciplines 

References

Urtsev V. N., Shmakov A. V., Urtsev N. V. etc. Phenomenological Model of Austenite Decomposition Kinetics

in Low-Carbon Low-Alloy High-Strength Steels // Steel in Translation. 2020. V. 50. P. 496–500. DOI:

3103/S0967091220070153.

Xie Q., Suvarna M., Li J. etc. Online prediction of mechanical properties of hot rolled steel plate using machine

learning // Materials & Design. 2021. V. 197. 109201. DOI: 10.1016/j.matdes.2020.109201.

Bhattacharyya T., Singh S. B., Dey S. etc. Microstructural prediction through artificial neural network (ANN) for

development of transformation induced plasticity (TRIP) aided steel // Materials Science and Engineering: A.

V. 565. P. 148‒157. DOI: 10.1016/j.msea.2012.11.110.

Isasti N., García-Riesco P. M., Jorge-Badiola D. etc. Modeling of CCT Diagrams and Ferrite Grain Size Prediction in Low Carbon Nb‒Mo Microalloyed Steels // ISIJ International. 2015. V. 55. № 9. P. 1963‒1972. DOI:

2355/isijinternational.ISIJINT-2015-036.

Umemoto M., Nishioka N., Tamura I. Prediction of hardenability from isothermal transformation diagrams //

Journal of Heat Treating. 1981. V. 2. № 2. P. 130–138. DOI:10.2355/isijinternational1966.22.629.

Umemoto M., Komatsubara N., Tamura I. Prediction of hardenability effects from isothermal transformation

kinetics // Journal of Heat Treating. 1980. V. 1. № 3. P. 57–64. DOI: 10.1007/BF02833039.

Lee J.-Y., Kim M., Lee Y.-K. Design of high strength medium-Mn steel using machine learning // Materials

Science and Engineering. 2022. V. 843. 143148. DOI: 10.1016/j.msea.2022.143148.

Cui C., Cao G., Li X. etc. A strategy combining machine learning and physical metallurgical principles to predict

mechanical properties for hot rolled Ti micro-alloyed steels // Journal of Materials Processing Technology. 2023.

V. 311. 117810. DOI: 10.1016/j.jmatprotec.2022.117810.

Lu Q., Lui S., Li W., Jin X. Combination of thermodynamic knowledge and multilayer feedforward neural networks for accurate prediction of MS temperature in steels // Materials & Design. 2020. V. 192. 108696. DOI:

1016/j.matdes.2020.108696.

Zhang Y., Ling C. A strategy to apply machine learning to small datasets in materials science // Npj Computational Materials. 2018. V. 4. 25. DOI: 10.1038/s41524-018-0081-z.

Lancaster F. Metallurgy of Welding. — Abington, Cambridge: Abington Pub., 1999. — 468 p.

Gafarov M., Okishev K., Makovetskiy A. Predicting the Hardness of Pipe Steels Using Machine Learning Methods // 2022 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM),

P. 1051−1056.

Окишев К. Ю., Гафаров М. Ф., Павлова К. П. и др. Построение и анализ моделей предсказания пределов

текучести трубных сталей после термической обработки с помощью методов машинного обучения // Кузнечно-штамповочное производство. Обработка материалов давлением. 2022. № 10. С. 10−17.

Попова Л. Е., Попов А. А. Диаграммы превращения аустенита в сталях и бета-раствора в сплавах титана.

Справочник термиста. — 3-е изд., перераб. и доп. — М.: Металлургия, 1991. — 503 с.

Vander Voort G. F. Atlas of Time-Temperature Diagrams for Irons and Steels. — ASM International, 1991. — 766 p.

Atlas zur Wärmebehandlung der Stähle // Zusammenarbeit mit dem Werkstoffausschuss des Vereins Deutscher

Eisenhüttenleute. Max-Planck-Institute für Eisenforschung. 1954. V. 2. Verlag Stahleisen. — 252 p.

Krauss G. Steels: Processing, Structure, and Performance. — ASM International, Materials Park, Ohio. 2005. — 613 p.

Maaten L. J. P., Hinton G. E. Visualizing High-Dimensional Data Using t-SNE // Journal of Machine Learning

Research. 2008. V. 9. P. 2579−2605.

Schubert E., Sander J., Ester M. etc. DBSCAN revisited, revisited: why and how you should (still) use DBSCAN

// ACM Transactions on Database Systems (TODS). 2017. V. 42. № 3. P. 19. DOI: 10.1145/3068335.

URL: http://jmatpro.ru/ (дата обращения: 09.08.2023).

Окишев К. Ю. Расчет диаграмм изотермического распада аустенита в конструкционных сталях // Вестник

ПНИПУ. Машиностроение, материаловедение. 2020. № 2. С. 82–89.

Cahn J. W. The kinetics of grain boundary nucleated reactions // Acta Metallurgica. 1956. V. 4. №. 5. P. 449–

DOI:10.1016/0001-6160(56)90041-4.

URL: https://scikit-learn.org/stable/ (дата обращения: 12.08.2023).

URL: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html (дата обращения: 12.08.2023).

Ojala M., Gemma C. Permutation Tests for Studying Classifier Performance // The Journal of Machine Learning

Research. 2010. V. 11. P. 1833–1863. DOI:10.5555/1756006.1859913.

URL: https://scikitlearn.org/stable/modules/generated/sklearn.metrics.mean_absolute_error.html (дата обращения: 12.08.2023).

Гмурман В. Е. Руководство к решению задач по теории вероятностей и математической статистике. —

М.: Высшая Школа, 1979. — 400 с.

Efron B. Bootstrap Methods: Another Look at the Jackknife // The Annals of Statistics. 1979. V. 7. P. 1‒26. DOI:

1214/aos/1176344552.

Брейман Л. «Случайные леса» // Машинное обучение. 2001. Т. 45. № 1. С. 5−32.

ГОСТ 5639−82. Стали и сплавы. Методы выявления и определения величины зерна. — М.: Издательство

стандартов, 2003. — 21 с.

Published

2026-06-18

Issue

Vol. 80 No. 1 (2024)

Section

Сталеплавильное производство

License

Copyright (c) 2024 ЧЕРНАЯ МЕТАЛЛУРГИЯ. Бюллетень научно-технической и экономической информации

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite

MODELING OF DECOMPOSITION PRODUCTS OF SUPERCOOLED AUSTENITEIN PIPE STEELS USING ARTIFICIAL INTELLIGENCE METHODS. (2026). Ferrous Metallurgy. Bulletin of Scientific , Technical and Economic Information, 80(1), 38-47. https://doi.org/10.32339/0135-5910-2024-1-38-47