Paper Titles
Modeling of the Diffusion Process of Nitrogen Redistribution in Steel during Complex Ion Nitriding
p.3
Influence of Carbon Content on the Strengthening Characteristics of Steels during AFSH
p.11
Study of the Kinetics of Plastic Deformation Propagation in a Welded Joint of 10G2FB Steel after Submerged Arc Welding
p.19
Microstructural Effects on the Fragmentation of High-Carbon Steel Cylindrical Shells under Explosive Loading
p.31
Steel Microstructure Prediction Mechanism Using Convolutional Neural Networks
p.39
Effect of Si Content on Property of Al-Si-Mg Strip Cast Using High Speed Twin Roll Caster
p.47
Microstructural and Mechanical Properties of Flash SPS WC-Co/AISI 304L Diffusion Bonded
p.53
Effect of Impurity on Casting of Al-25%Si Heat Sink with Thin Fins
p.59
Effect of Mold Lubricant on Flow Length of Al-Mg Alloy in Die Casting
p.65

Steel Microstructure Prediction Mechanism Using Convolutional Neural Networks

Article Preview

Abstract:

Accurate prediction of steel microstructure is critical for ensuring desirable mechanical properties in industrial applications. This research integrates metallurgical transformation models into a convolutional neural network (CNN) for the classification and quantitative analysis of steel microstructures, including ferrite, pearlite, bainite, and martensite. The model utilizes image-based grain structure recognition in combination with explicit mathematical relations, such as the Hall-Petch equation for yield strength, the Koistinen-Marburger equation for martensitic transformation, and the Avrami equation for ferrite and pearlite phase fraction prediction. By implementing these relations within a Python-based machine learning framework, the network not only classifies steel phases but also estimates grain size, transformation kinetics, and mechanical properties. The developed approach achieves an accuracy of over 90% in microstructure classification and enables real-time prediction of metallurgical characteristics from microstructure images. This research provides a new avenue for computational material science by integrating data-driven neural networks with fundamental physical models.

You might also be interested in these eBooks
Building Materials, Steel and Alloys: Properties and Processing View Preview

Info:

Periodical:

Materials Science Forum (Volume 1163)

Pages:

39-46

DOI:

https://doi.org/10.4028/p-7hpDXC

Citation:

Cite this paper

Online since:

October 2025

Authors:

Serhii Fedoriachenko, Kyrylo Ziborov, Ivan Lutsenko, Dmytro Harkavenko*

Keywords:

Convolutional Neural Networks, Machine Learning, Metallurgical Phase Classification, Microstructural Image Analysis, Steel Microstructure Prediction, Transformation Kinetics in Steel

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2025 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] Iren, D., Ackermann, M. A., Gorfer, J., Pujar, G., & Brekel, D. (2021). Aachen-Heerlen annotated steel microstructure dataset. Scientific Data, 8(1), 1-10.

DOI: 10.1038/s41597-021-00926-7

Google Scholar

[2] Koistinen, D. P., & Marburger, R. E. (1959). A general equation prescribing the extent of the austenite-martensite transformation in pure iron-carbon alloys and plain carbon steels. Acta Metallurgica, 7(1), 59-60.

DOI: 10.1016/0001-6160(59)90170-1

Google Scholar

[3] Bhadeshia, H. K. D. H. (2000). Application of Koistinen and Marburger's athermal equation for volume fraction of martensite to diffusional transformations obtained on continuous cooling. Materials Science and Technology, 16(12), 1409-1411.

DOI: 10.1179/026708300101508397

Google Scholar

[4] Huyan, F., Hedström, P., & Borgenstam, A. (2015). Modelling of the fraction of martensite in low-alloy steels. Materials Today: Proceedings, 2(S), S561-S564.

DOI: 10.1016/j.matpr.2015.07.347

Google Scholar

[5] Lutsenko I., Rukhlova N., Kyrychenko M., Tsyhan P., Panchenko V. (2023), Increasing the energy efficiency of modes of distribution networks with photovoltaic stations, Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (1), p.99 – 106.

DOI: 10.33271/nvngu/2023-1/099

Google Scholar

[6] Mygal, V.P., Mygal, G.V., Balabanova, L.M. (2019). Visualization of signal structure showing element functioning in complex dynamic systems – Cognitive aspects (2019) Journal of Nano- and Electronic Physics, 11/2). № 02013.

DOI: 10.21272/jnep.11(2).02013

Google Scholar

[7] Slyusar, V., Protsenko, M., Chernukha, A., Gornostal, S., Rudakov, S., Shevchenko, S., Chernikov, O., Kolpachenko, N., Timofeyev, V., Artiukh, R. (2021). Construction of an advanced method for recognizing monitored objects by a convolutional neural network using a discrete wavelet transform. Eastern-European Journal of Enterprise Technologies, 4/9 (112), 65–77.

DOI: 10.15587/1729-4061.2021.238601

Google Scholar

[8] Tulskyi, H., Liashok, L., Shevchenko, H., Vasilchenko, A., Stelmakh, O. (2019). Synthesis of functional nanocomposites based on aluminum oxide Functional Materials, 26/4, 718–722.

Google Scholar

[9] Petryshchev, A., Milko, D., Borysov, V., Tsymbal, B., Hevko, I., Borysova, S., Semenchuk, A. (2019). Studying the physical-chemical transformations at resourcesaving reduction melting of chromenickelcontaining metallurgical waste. Eastern-European Journal of Enterprise Technologies, 2/12 (98), 59–64.

DOI: 10.15587/1729-4061.2019.160755

Google Scholar

[10] Vambol, S., Vambol, V., Suchikova, Y., Bogdanov, I., Kondratenko, O. (2018). Investigation of the porous GaP layers' chemical composition and the quality of the tests carried out. Journal of Achievements in Materials and Manufacturing Engineering, 86/2, 49–60.

DOI: 10.5604/01.3001.0011.8236

Google Scholar

[11] Pivniak H., Aziukovskyi O., Papaika Yu., Lutsenko I., Neuberger N. (2022), Problems of development of innovative power supply systems of Ukraine in the context of European integration, Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu (5), p.89 – 103.

DOI: 10.33271/nvngu/2022-5/089

Google Scholar

[12] Kuprikov, V., Pilipenko, V., Soznik, A. (2006). Analysis of nucleon-nucleus scattering in terms of a microscopic optical potential based on effective Skyrme forces Physics of Atomic Nuclei, 69/1, 6–15.

DOI: 10.1134/s1063778806010029

Google Scholar

[13] Pasternak, V., Samchuk, L., Huliieva, N., Andrushchak, I., Ruban, A. (2021). Investigation of the properties of powder materials using computer modeling. Materials Science Forum, 1038 MSF, 33–39.

DOI: 10.4028/www.scientific.net/msf.1038.33

Google Scholar

[14] Laukhin D., Ziborov K., Rott N., Fedoriachenko S. (2024) Analysis of the Effects of Welding Conditions on the Microhardness of Low-Carbon Low-Alloy Steels, Materials Science Forum, 1126, p.119 – 127.

DOI: 10.4028/p-ld0xwa

Google Scholar

[15] Franchuk V.P., Ziborov K.A., Krivda V.V., Fedoriachenko S.O. (2018), Influence of thermophysical processes on the friction properties of wheel - rail pair in the contact area, Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (2), p.46 – 52.

DOI: 10.29202/nvngu/2018-2/7

Google Scholar

[16] Ziborov K.A.; Protsiv V.V.; Blokhin S.Ye.; Fedoriachenko S.O. (2014), Applicability of computer simulation while designing mechanical systems of mining rolling stock, Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, Vol. 6, pp.55-59.

Google Scholar

[17] Laukhin, D., Poznyakov, V., Kostin, V., Beketov, O., Rott, N., Slupska, Y., ... & Liubymova-Zinchenko, O. (2021). Features In The Formation Of The Structural State Of Lowcarbon Micro-Alloyed Steels After Eletron Beam Welding. Eastern-European Journal of Enterprise Technologies, 111(12).

DOI: 10.15587/1729-4061.2021.234783

Google Scholar