Abstract
For modern electric installations to be competitive, they should be supported by numerical simulations of high quality and accuracy. In turn, to improve the accuracy of numerical simulation of electric installations, it is required to take into account the thermal-physical, electromagnetic, and mechanical properties of materials as much as possible. This article discusses the possibility of predicting the properties of carbon steels on the basis of their chemical composition for a wide temperature range using a set of artificial neural networks as exemplified by electrical resistivity. Training and verification of neural networks have been based on experimental data from reference books and databases. The methods have been applied so as to avoid retraining of neural networks, as well as to use initial data more completely. The training results of neural networks are given, the error level is evaluated, and the potential is determined of applying neural networks to production of material properties and, as a consequence, improving simulation quality.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Gavard, L., Bhadeshia, H.K.D.H., and MacKay, D.J.C., Bayesian neural network model for austenite formation in steels, Mater. Sci. Technol., 1996, vol. 12.
Bhadeshia, H.K.D.H. Neural networks in materials science, ISIJ Int., 1999, vol. 39, no. 10.
Peet, M.J., Hasan, H.S., and Bhadeshia, H.K.D.H., Prediction of thermal conductivity of steel, Int. J. Heat Mass Transfer, 2011, vol. 54, nos. 11–12.
Žmak, I. and Filetin, T., Predicting thermal conductivity of steels using artificial neural networks, Trans. FAMENA, 2010, vol. 34, no. 3.
Koley, S., Ray, T., Mohanty, I., et al., Prediction of electrical resistivity of steel using artificial neural network, Ironmaking Steelmaking, 2019, vol. 46, no. 4.
Smithells Metals Reference Book, Gale, W.F. and Totemeier, T.C., Eds., Amsterdam: Elsevier, 2004, 8th ed.
ASM Handbook, Vol. 1: Properties and Selection: Irons, Steels, and High-Performance Alloys, Cleveland, OH: ASM Int., 1990.
MatWeb, Material property data. http://www.matweb.com/search/PropertySearch.aspx. Accessed September 22, 2019.
Fizicheskie svoistva stalei i splavov, primenyaemykh v energetike: Spravochnik (Physical Properties of Steels and Alloys Used in Energetics), Neimark, B.E., Ed., Moscow: Energiya, 1967.
Teplofizicheskie svoistva veshchestv. Spravochnik (Thermophysical Properties of Substances: Handbook), Vargaftik, N.B., Ed., Moscow: Gosenergoizdat, 1956.
Bugardt, K. and Spyra W., Wärmeleitfähigkeit unlegierter und legierter Stähle und Legierungen bei Temperaturen zwischen 20 und 700°C, Arch. Eisenhüttenwesen, 1965, vol. 36, no. 4.
Richter, F., The physical properties of steels, in The 100 Steels Program, Part 1: Tables and Figures, Mülheim an der Ruhr, 2010.
Physical Constants of Some Commercial Steels at Elevated Temperatures, London: Butterworth, 1953.
MacKay, D.J.C., Bayesian interpolation, Neural Comput., 1992, vol. 4, no. 3, p. 41.
MacKay, D.J.C., A practical Bayesian framework for backpropagation networks, Neural Comput., 1992, vol. 4, no. 3, pp. 448–472.
Bondar, A.S. and Chmilenko, F.V., The use of a neural network to obtain the characteristics of steels depending on the chemical composition, 2019 IEEE Conf. Russian Young Researchers in Electrical and Electronic Engineering (2019 ElConRus), St. Petersburg, 2019.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by I. Moshkin
About this article
Cite this article
Chmilenko, F.V., Bondar, A.S., Streltsova, O.V. et al. Prediction of Physical Properties of Steels Using Artificial Neural Networks for Numerical Simulation of Electrical Installations. Russ. Electr. Engin. 90, 807–811 (2019). https://doi.org/10.3103/S1068371219120046
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068371219120046