Abstract
Process of building machine learning models to predict microstructures of pipe steels after continuous cooling involves the collection and preparation of data, the source of which is thermokinetic diagrams of supercooled austenite decomposition. Statistics of intermediate and final data, as well as algorithms for their transformation are given. Evaluations of machine learning models for selected microstructures are considered. A method for generating data under small sample conditions and introducing an evaluative feature of grain size are proposed. Models were validated and the significance of features was interpreted. The practical use of models for constructing thermokinetic diagrams of austenite decomposition and analysis of modeling results is shown.
REFERENCES
Urtsev, V.N., Shmakov, A.V., Urtsev, N.V., Mokshin, E.D., Khabibulin, D.M., Degtyarev, V.N., Stekanov, P.A., Gornostyrev, Yu.N., Lobanov, M.L., Platov, S.I., and Maslennikov, K.B., Phenomenological model of austenite decomposition kinetics in low-carbon low-alloy high-strength steels, Steel Transl., 2020, vol. 50, no. 7, pp. 496–500. https://doi.org/10.3103/s0967091220070153
Xie, Q., Suvarna, M., Li, J., Zhu, X., Cai, J., and Wang, X., Online prediction of mechanical properties of hot rolled steel plate using machine learning, Mater. Des., 2021, vol. 197, p. 109201. https://doi.org/10.1016/j.matdes.2020.109201
Bhattacharyya, T., Singh, S.B., Dey, S.S., Bhattacharyya, S., Bleck, W., and Bhattacharjee, D., Microstructural prediction through artificial neural network (ANN) for development of transformation induced plasticity (TRIP) aided steel, Mater. Sci. Eng., A, 2013, vol. 565, pp. 148–157. https://doi.org/10.1016/j.msea.2012.11.110
Isasti, N., García-Riesco, P.M., Jorge-Badiola, D., Taheri, M., López, B., and Uranga, P., Modeling of CCT diagrams and ferrite grain size prediction in low carbon Nb–Mo microalloyed steels, ISIJ Int., 2015, vol. 55, no. 9, pp. 1963–1972. https://doi.org/10.2355/isijinternational.ISIJINT-2015-036
Jeon, J., Seo, N., Jung, J.-G., Kim, H.-S., Son, S.B., and Lee, S.-J., Prediction and mechanism explain of austenite-grain growth during reheating of alloy steel using XAI, J. Mater. Res. Technol., 2022, vol. 21, pp. 1408–1418. https://doi.org/10.1016/j.jmrt.2022.09.119
Umemoto, M., Nishioka, N., and Tamura, I., Prediction of hardenability from isothermal transformation diagrams, J. Heat Treat., 1981, vol. 2, no. 2, pp. 130–138. https://doi.org/10.1007/bf02833229
Umemoto, M., Komatsubara, N., and Tamura, I., Prediction of hardenability effects from isothermal transformation kinetics, J. Heat Treat., 1980, vol. 1, no. 3, pp. 57–64. https://doi.org/10.1007/bf02833039
Lee, J.-Yo., Kim, M., and Lee, Yo.-K., Design of high strength medium-Mn steel using machine learning, Mater. Sci. Eng., A, 2022, vol. 843, p. 143148. https://doi.org/10.1016/j.msea.2022.143148
Cui, C., Cao, G., Li, X., Gao, Z., Liu, J., and Liu, Z., A strategy combining machine learning and physical metallurgical principles to predict mechanical properties for hot rolled Ti micro-alloyed steels, J. Mater. Process. Technol., 2023, vol. 311, p. 117810. https://doi.org/10.1016/j.jmatprotec.2022.117810
Lu, Q., Liu, S., Li, W., and Jin, X., Combination of thermodynamic knowledge and multilayer feedforward neural networks for accurate prediction of MS temperature in steels, Mater. Des., 2020, vol. 192, p. 108696. https://doi.org/10.1016/j.matdes.2020.108696
Zhang, Yi. and Ling, C., A strategy to apply machine learning to small datasets in materials science, npj Comput. Mater., 2018, vol. 4, no. 1, p. 25. https://doi.org/10.1038/s41524-018-0081-z
Lancaster, F., Metallurgy of Welding, Abington, Pa.: Abington Publishing, 1999.
Gafarov, M., Okishev, K., and Makovetskiy, A., Predicting the hardness of pipe steels using machine learning methods, 2022 Int. Conf. on Industrial Engineering, Applications and Manufacturing (ICIEAM), Sochi, Russia, 2022, IEEE, 2022, pp. 1051–1056. https://doi.org/10.1109/icieam54945.2022.9787169
Okishev, K.Yu., Gafarov, M.F., Pavlova, K.P., et al., Construction and analysis of forecasting models of yield strengths of pipe steels after heat treatment using machine learning methods, Kuznechno-Shtampovochnoe Proizvod. Obrab. Mater. Davleniem, 2022, no. 10, pp. 10–17.
Popova, L.E. and Popov, A.A., Diagrammy austenitnogo prevrashcheniya v stalyakh i beta-rastvora v splavakh titana (Diagrams of Austenite Transformation in Steels and Beta-Solution in Titanium Alloys), Moscow: Metallurgiya, 1991.
Vander Voort, G.F., Atlas of Time-Temperature Diagrams for Irons and Steels, Materials Park, Ohio: ASM Int., 1991.
Atlas zur Wärmebehandlung der Stähle, Düsseldorf: Stahleisen, 1954, vol. 2.
Krauss, G., Steels: Processing, Structure, and Performance, Materials Park, Ohio: ASM Int., 2005.
Okishev, K.Yu., Calculation of ttt diagrams of isothermal austenite decomposition in structural steels, Vestn. Permsk. Nats.-Issled. Univ., Mashinostr., Materialoved., 2020, vol. 22, no. 2, pp. 82–89. https://doi.org/10.15593/2224-9877/2020.2.10
Maaten, L.J.P. and Hinton, G.E., Visualizing high-dimensional data using t-SNE, J. Mach. Learn. Res., 2008, vol. 9, pp. 2579–2605.
Schubert, E., Sander, J., Ester, M., Kriegel, H.P., and Xu, X., DBSCAN Revisited, Revisited: Why and how you should (still) use DBSCAN, ACM Trans. Database Syst., 2017, vol. 42, no. 3, p. 19. https://doi.org/10.1145/3068335
JMatPro: Software for modeling multicomponent steels and alloys. http://jmatpro.ru/.
JMatPro demo version. http://jmatpro.ru/#article.
Guo, Z., Saunders, N., Miodownik, P., and Schillé, J., Modelling phase transformations and material properties critical to the prediction of distortion during the heat treatment of steels, Int. J. Microstructure Mater. Properties, 2009, vol. 4, no. 2, pp. 187–195. https://doi.org/10.1504/IJMMP.2009.028632
Cahn, J.W., The kinetics of grain boundary nucleated reactions, Acta Metall., 1956, vol. 4, no. 5, pp. 449–459. https://doi.org/10.1016/0001-6160(56)90041-4
Ojala, M. and Garriga, G.C., Permutation tests for studying classifier performance, 2009 Ninth IEEE Int. Conf. on Data Mining, Miami Beach, Fla., 2010, IEEE, 2010, pp. 1833–1863. https://doi.org/10.1109/icdm.2009.108
Machine learning in Python. https://scikit-learn.org/stable/.
LightGBM: gradient boosting framework that uses tree based learning algorithms. https://lightgbm.readthedocs.io/en/v3.3.2/.
Supervised learning. https://scikit-learn.org/stable/supervised_learning.html#supervised-learning.
GridSearchCV: Exhaustive search over specified parameter values for an estimator. https://scikit-learn.org/ stable/modules/generated/sklearn.model_selection.GridSearchCV.html.
https://scikitlearn.org/stable/modules/generated/sklearn.metrics.mean_absolute_error.html.
Gmurman, V.E., Rukovodstvo k resheniyu zadach po teorii veroyatnostei i matematicheskoi statistike (Guidelines to Solving Problems of the Probability Theory and Mathematical Statistics), Moscow: Vysshaya Shkola, 1979.
Efron, B., Bootstrap methods: Another look at the jackknife, Ann. Stat., 1979, vol. 7, no. 1, pp. 1–26. https://doi.org/10.1214/aos/1176344552
Breiman, L., Random forests, Mach. Learn., 2001, vol. 45, pp. 5–32. https://doi.org/10.1023/A:1010933404324
GOST (State Standard) 5639–82: Steels and alloys. Methods for detection and determination of grain size, 1983.
Funding
This work was supported by ongoing institutional funding. No additional grants to carry out or direct this particular research were obtained.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Translated by V. Selikhanovich
Publisher’s Note.
Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Gafarov, M.F., Okishev, K.Y., Makovetskiy, A.N. et al. Construction of Models for Predicting the Microstructure of Steels after Heat Treatment Using Machine Learning Methods. Steel Transl. 53, 1120–1129 (2023). https://doi.org/10.3103/S0967091223110104
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0967091223110104