Modeling of changes in heat resistance of nickel-based alloys using Bayesian artificial neural networks

O.V. Anoshina, A.S. Trubnikova, O.B. Milder, D.A. Tarasov, A.A. Ganeev ORCID logo , A.G. Tyagunov show affiliations and emails
Received 26 September 2019; Accepted 20 December 2019;
This paper is written in Russian
Citation: O.V. Anoshina, A.S. Trubnikova, O.B. Milder, D.A. Tarasov, A.A. Ganeev, A.G. Tyagunov. Modeling of changes in heat resistance of nickel-based alloys using Bayesian artificial neural networks. Lett. Mater., 2020, 10(1) 106-111
BibTex   https://doi.org/10.22226/2410-3535-2020-1-106-111

Abstract

The graphs of the dependences of heat resistance on the Larson-Miller parameter have the form characteristic of all the alloys studied, but for each melting composition there are individual characteristics. The calculated and experimental values of heat resistance have satisfactory convergence.Resource design of gas turbine engines and installations requires extensive information about the heat resistance of nickel-based superalloys, from which the most critical parts of aircraft and marine engines, pumps of gas-oil pumping stations and power plants are made. The problems are that the data on the heat resistance obtained as a result of testing each alloy under study are quite limited. In the present paper, the task of modelling changes in the heat resistance of nickel-based superalloy on the basis of available experimental data is solved. To solve the task, the most modern approach, the neural network modeling method, was applied. The input data are chemical compositions of heat-resistant nickel-based superalloys and the values of their heat resistance obtained experimentally. The output data are the calculated values of heat resistance modeled by an artificial neural network. In the course of the work, transformations of the input data were carried out to reduce the standard deviation of the modeling of the output data. The choice of the neural network configuration was made in order to achieve the highest possible accuracy. As a result, a neural network of direct error propagation was used, with 27 neurons on the input layer, 13 neurons in the hidden layer and 1 neuron in the output layer. To validate the results of the predictions, a group of alloys with the maximum number of known experimental values of heat resistance was randomly selected before the input of data into the network. After preparing the data, selecting the configuration and training the network, the chemical compositions of the selected group were loaded and their heat resistance values were calculated. Comparison of the obtained data with the experimental data showed high efficiency of the method. As a result, data on the change of heat resistance for the studied alloys were obtained and an analytical expression describing the obtained dependences was formulated.

References (21)

1. Ch. T. Sims. Superalloys II: High-Temperature Materials for Aerospace and Industrial Power (ed. by Ch. T. Sims, N. S. Stoloff, W. K. Hagel). New York, Wiley (1987) 640 p.
2. C. R. Reed. The Superalloys. Fundamentals and Applicatios. Cambridge University Press (2006) 372 p. Crossref
3. E. N. Kablov, V. V. Gerasimov, E. M. Visik. Aviation Industry. 2, 18 (1999). (in Russian) [Е. Н. Каблов, В. В. Герасимов, Е. М. Висик. 2, 18 (1999).].
4. Yu. M. Lakhtin, V. P. Leontyev. Materialovedeniye. Moscow, Mashinostroenie (1990) pp. 16 - 18. (in Russian) [Ю. М. Лахтин, В. П. Леонтьева. Материаловедение Москва, Машиностроение (1990) c. 16 - 18.].
5. GOST 10145-81 Metals. Metod ispytaniya na dlitel'nuyu prochnost'. Moscow, Izdatel'stvo standartov (1981). (in Russian) [ГОСТ 10145 - 81 Металлы. Метод испытания на длительную прочность. Москва, Издательство стандартов (1981).].
6. B. N. Sinayski, M. S. Belyaev, N. D. Zhukov, A. D. Panteleev. Strength of Materials. 21, 322 (1989). Crossref
7. M. H. Beale, M. T. Hagan, H. B. Demuth. Matlab Neural Network Toolbox User’s Guide. Mathworks (2018) 558 p.
8. S. Khaikin. Neyronnyye seti: Polnyy kurs. Moscow: Williams (2017) 1104 p. (in Russian) [С. Хайкин. Нейронные сети: Полный курс. Москва, Вильямс (2017) 1104с.].
9. P. D. Wasserman. Neural Computing: Theory and Practice. Coriolis Group (1989) 230 p.
10. R. Callan. Osnovnyye kontseptsii neyronnykh setey. Moscow, Williams (2001) 288 p. (in Russian) [Р. Каллан. Основные концепции нейронных сетей. Москва, Вильямс (2001) 288 с.].
11. G. I. Ivchenko, Yu. I. Medvedev. Matematicheskaya statistika. Textbook. Moscow, Liberkom (2014) 352 p. (in Russian) [Г. И. Ивченко, Ю. И. Медведев. Математическая статистика. Учебник. Москва, Либерком (2014) 288 с.].
12. A. G. Tyagunov, E. E. Baryshev, T. K. Kostina, B. A. Baum, V. P. Lesnikov, I. P. Semenova. Phys. Metal. Metallogr. 86, 65 (1998).
13. A. G. Tyagunov, E. E. Baryshev, T. K. Kostina, I. P. Semenova, V. P. Lesnikov. Metal Science and Heat Treatment. 41, 538 (1999). Crossref
14. V. P. Kuznetsov, V. P. Lesnikov, N. A. Popov. Struktura i svoystva zharoprochnykh nikelevykh splavov. Publishing house of the Ural University (2016) 164 р. (in Russian) [В. П. Кузнецов, В. П. Лесников, Н. А. Попов. Структура и свойства жаропрочных никелевых сплавов. Издательство Уральского университета (2016) 164 с.].
15. E. N. Kablov. Lityye lopatki gazoturbinnykh dvigateley. Splavy, tekhnologiya, pokrytiya. Moscow, MISIS (2001) 632 р. (in Russian) [Е. Н. Каблов. Литые лопатки газотурбинных двигателей. Сплавы, технология, покрытия. Москва, МИСИС (2001) 632 с.].
16. A. V. Logunov, Yu. N. Smolin. Sovremennyye zharoprochnyye nikelevyye splavy dlya diskov gazovykh turbin. Moscow, Nauka I Tekhnologii (2013) 264 p. (in Russian) [А. В. Логунов, Ю. Н. Шмотин. Современные жаропрочные никелевые сплавы для дисков газовых турбин. Москва, Наука и технологии (2013) 264 с.].
17. S. V. Gaiduk, T. V. Tikhomirova. Aerospace engineering and technology. 9, 33 (2015). (in Russian) [С. В. Гайдук, Т. В. Тихомирова. Авиационно-космическая техника и технология. 9, 33 (2015).].
18. S. V. Gaiduk, V. V. Kononov, V. V. Kurenkova. General issues of metallurgy. 4, 31 (2015). (in Russian) [С. В. Гайдук, В. В. Кононов, В. В. Куренкова. Общие вопросы металлургии. 4, 31 (2015).].
19. S. V. Gaiduk, V. V. Kononov, V. V. Kurenkova. Electrometallurgy today. 4 (129), 44 (2017). (in Russian) [С. В. Гайдук, В. В. Кононов, В. В. Куренкова. Современная электрометаллургия. 4 (129), 44 (2017).]. Crossref
20. E. N. Kablov, O. G. Ospennikova, N. V. Petrushin, E. M. Visik. Aviation materials and technologies. 2, 14 (2015). (in Russian) [Е. Н. Каблов, О. Г. Оспенникова, Н. В. Петрушин, Е. М. Висик. Авиационные материалы и технологии. 2, 14 (2015).]. Crossref
21. E. N. Kablov, O. G. Ospennikova, N. V. Petrushin. Aviation materials and technologies. 1, 34 (2015). (in Russian) [Е. Н. Каблов, О. Г. Оспенникова, Н. В. Петрушин. Авиационные материалы и технологии. 1, 34 (2015).]. Crossref

Similar papers