Abstract
A neural network may be used to predict alloy strength with high accuracy in a minimum of iterations. The corresponding organization of the network structure and selection of the optimal training algorithm is considered for the example of Al–Ca–Mn alloys.
REFERENCES
Beletskii, V.M. and Krivov, G.A., Alyuminievye splavy (sostav, svoistva, tekhnologiya, primenenie): Spravochnik (Aluminum Alloys (Composition, Properties, Technology, Application): Handbook), Fridlyander, I.N, Ed., Kiev: Komintekh, 2005.
Shemetev, G.F., Alyuminievye splavy: Sostavy, svoistva, primenenie: Uchebnoe posobie po kursu “Proizvodstvo otlivok iz splavov tsvetnykh metallov” (Aluminum Alloys: Compositions, Properties, Application: Manual on the Course “Production of Non-Ferrous Metal Alloy Castings”), St. Petersburg, 2012, part 1.
Mutylina, I.N., Materialovedenie. Tsvetnye metally i splavy na ikh osnove:Uchebno-metodicheskii kompleks (Materials Science. Non-Ferrous Metals and Alloys on Their Basis: Educational and Methodical Complex), Moscow: Prospekt, 2019.
Lemzikov, A.V., Kundas, S.P., Kutsylo, V.V., and Ivanov, D.G., Artificial neural networks implementation for prediction of characteristic points of phase transformations in steels with a wide range of chemical composition, Informatika, 2007, no. 1 (13), pp. 89–97.
Lemzikov, A.V. and Kundas, S.P., Training artificial neural networks for predicting properties of steels, Informatika, 2009, no. 4 (24), pp. 101–111.
Nurgayanova, O.S. and Yusupova, N.I., Training a neural network to predict the properties of nickel alloys with a genetic algorithm, Tr. Inst. Sist. Anal. Ross. Akad. Nauk, 2019, vol. 69, no. 4, pp. 22–28.
Bol’shakov, A.E. and Lovushkin, M.Yu., Prognosis compositions aluminum alloys according to their properties, Mashinostr. Bezopasn. Zhiznedeyat., 2011, no. 2 (9), pp. 37–43.
Nurgayanova, O.S., Application of artificial neural networks in the tasks of classification of multicomponent alloys, Proc. 6th All-Russian Sci. Conf. “Information Technologies for Intelligent Decision Making Support”, 2018, vol. 3.
Tukhvatulin, I.Kh. and Lankin, Yu.P., Prediction of metal alloy properties using neural networks, Trudy II Vserossiiskoi nauchno-tekhnicheskoi konferentsii “Neiroinformatika-2000” (Nauchnaya sessiya MIFI-2000) (Proc. II All-Russian Sci.-Tech. Conf. “Neuroinformatics-2000” (Sci. Session of MEPhI-2000)), Moscow: Mosk. Inzh.-Fiz. Inst., 2000, part 2, pp. 119–125.
Tukhvatulin, I.Kh., Kolokol’tsev, V.M., Dolgopolo-va, L.B., and Lankin, Yu.P., Metallurgical neural network expert system for assessing the properties of alloys and issuing practical recommendations, Litein. Proizvod., 2000, no. 3, pp. 6–8.
Lankin, Yu.P., Kolokol’tsev, V.M., Tukhvatulin, I.Kh., and Dolgopolova, L.B., Using neural network methods to create new alloys, Izv. Vyssh. Uchebn. Zaved., Chern. Metall., 2000, no. 11, pp. 44–48.
Nurgayanova, O.S. and Yusupova, N.I., Training a neural network to predict the properties of nickel alloys with a genetic algorithm, Tr. Inst. Sist. Anal. Ross. Akad. Nauk, 2019, vol. 69, no. 4, pp. 22–28.
Yusupova, N.I., Bogdanova, D.R., and Boiko, M.V., Obrabotka slabostrukturirovannoi informatsii na osnove metodov iskusstvennogo intellekta: Monografiya (Processing of Weakly Structured Information Based on Artificial Intelligence Methods: Monograph), Moscow: Innovats. Mashinostr., 2016.
Kharitonova, L.P., On the issue of neural network modeling to assess the energy consumption of large arrays of consumers (buildings), Mezhdunar. Nauch.-Issled. Zh., 2016, no. 8 (50), pp. 155–158. https://doi.org/10.18454/IRJ.2016.50.176
Pradhan, R.P. and Kumar, R., Forecasting exchange rate in India: An application of artificial neural network model, J. Math. Res., 2010, vol. 2, no. 4, pp. 111–117.
Bol’shakov, V.I., Dubrov, Yu.I., Tkachenko, A.N., and and Tkachenko, V.A., The task of identifying the qualitative characteristics of materials based on expert systems, Visn. Pridniprovsk. Derzh. Akad. Budiv. Arkh., 2010, no. 1, pp. 46–49.
Tukhvatulin, I.Kh. and Lankin, Yu.P., Prediction of metal alloy properties using neural networks, Trudy II Vserossiiskoi nauchno-tekhnicheskoi konferentsii “Neiroinformatika-2000” (Nauchnaya sessiya MIFI-2000) (Proc. II All-Russian Sci.-Tech. Conf. “Neuroinformatics-2000” (Sci. Session of MEPhI-2000)), Moscow: Mosk. Inzh.-Fiz. Inst., 2000, part 2, pp. 119–125.
Klochkova, K.V., Petrovich, S.V., and Abramova, V.V., Training a neural network using a genetic algorithm to predict the properties of cast irons with vermicular graphite, Grani Nauki, 2013, vol. 1, no. 2, pp. 104–107.
Kruglov, V.V. and Borisov, V.V., Iskusstvennye neironnye seti. Teoriya i praktika (Artificial Neural Networks. Theory and Practice), Moscow: Goryachaya Liniya–Telekom, 2002.
Rostovtsev, V.S., Iskusstvennye neironnye seti: Uchebnik (Artificial Neural Networks: Textbook), St. Petersburg: Lan’, 2019. ISBN 978-5-8114-3768-9. https://e.lanbook.com/book/122180. Accessed August 24, 2020.
Doroshenko, V.V., Processability of multicomponent aluminum-calcium alloys in casting and die machining, Cand. Sci. (Eng.) Dissertation, Moscow, 2019.
Letyagin, N.V., Effect of additional alloying (La, Cu, Mn) on structure, processability and mechanical properties of composite alumina-calcium alloys, Cand. Sci. (Eng.) Dissertation, Moscow, 2021.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by B. Gilbert
About this article
Cite this article
Simonova, L.A., Klochkova, K.V. & Bredinin, I.S. Predicting Alloy Strength by Neural Network Modeling: Al–Ca–Mn Alloys. Russ. Engin. Res. 43, 329–333 (2023). https://doi.org/10.3103/S1068798X23040305
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068798X23040305