ARTIFICIAL NEURAL NETWORK MODEL FOR PREDICTION OF MECHANICAL PROPERTIES OF STEEL
DOI:
https://doi.org/10.34185/1991-7848.itmm.2022.01.014Keywords:
artificial neural network, structural steels, mechanical properties, chemical compositionAbstract
The prediction of mechanical properties is very important task in the quality control of steel, which is one of the world's most important engineering and construction materials. To the main factors affecting the mechanical properties of steel belongs thermomechanical treatment and the chemical composition. The chemical composition may vary for a special high-strength low-alloy steel to meet certain mechanical property requirements. This paper presents a machine learning approach for prediction of tensile strength of structural steels. A single hidden layer Artificial Neural Network (ANN) model was developed and validated based on industrial data set. The ANN model inputs were parameters of interatomic interaction, characterizing the chemical and structural state of the melt. The modeling results showed that the ANN model might be an attractive and useful tool for forecasting the mechanical properties of steel. It offers also a potential for the further derivative free optimization of chemical composition for special quality criteria.
References
Li, X., Li, F., Cui, Y., Xiao, B., & Wang, X. (2016). The effect of manganese content on mechanical properties of high titanium microalloyed steels. Materials Science and Engineering A-structural Materials Properties Microstructure and Processing, 677, 340-348.
Qingshen, M., Leqing, H., Guobiao, D., Yanfeng, W.A., Yongda, Y., & Changwen, M. (2017). Effect of microalloying elements on microstructure and properties of quenched and tempered constructional steel. IOP Conf. Series: Materials Science and Engineering 242, doi:10.1088/1757-899X/242/1/012036.
Kalashnikov, I.S., Shalkevich, A., Acselrad, O., & Pereira, L.C. (2000). Chemical composition optimization for austenitic steels of the Fe-Mn-Al-C system. Journal of Materials Engineering and Performance, 9, 597-602.
Tregubenko, G.N. (2017). Improvement of the properties of low-alloy constructional steels microalloyed with the nitrogen-titan-aluminum complex. (in Russian). Металлургическая и горнорудная промышленность (Metallurgical and mining industry), 1, p. 67 – 71.
Babachenko, O., Kononenko, H., Snigura, I., & Togobytska, N. (2021). Optimisation of chemical composition of high-strength structural steels for achieving mechanical property requirements. Paper presented at ESAFORM 2021. 24th International Conference on Material Forming, Liège, Belgique. doi: 10.25518/esaform21.3654
Carneiro, M., Salis, T.T., Almeida, G.M., & Braga, A.P. (2021). Prediction of Mechanical Properties of Steel Tubes Using a Machine Learning Approach. Journal of Materials Engineering and Performance, 30, 434-443.
Pattanayak, S., Dey, S., Chatterjee, S., Chowdhury, S.G., & Datta, S. (2015). Computational intelligence based designing of microalloyed pipeline steel. Computational Materials Science, 104, 60-68.
Haykin S. (2009). Neural Networks and Learning Machines; Number Bd. 10 in Neural Networks and Learning Machines; Prentice Hall: Hamilton, ON, Canada.
Gurney, K. (2018). An Introduction to Neural Networks; CRC Press: London, UK
