FAR EASTERN BRANCH OF THE RUSSIAN ACADEMY OF SCIENCES
INSTITUTE OF APPLIED MATHEMATICS KHABAROVSK DIVISION
Far Eastern Mathematical Journal
Predicting subdifferential switching surface in a steady-state complex heat transfer problem using deep learning |
K.S. Kuznetsov, E.V. Amosova |
2022, issue 2, P. 190-194 DOI: https://doi.org/10.47910/FEMJ202224 |
Abstract |
| A boundary value problem of complex heat transfer have been considered in the work. A method for determination of a switching surface with subdifferential boundary conditions based on the use of deep learning has been proposed. A method uses a neural network trained on a dataset of numerical solutions of the steady-state complex heat transfer forward problems. The obtained results are verified by comparison with the numerical experiments. |
Keywords: subdifferential boundary value problem, deep learning, neural networks, complex heat transfer |
Download the article (PDF-file) |
References |
| [1] E. Schneider, M. Seaid, J. Janicka, A. Klar, “Validation of simplified PN models for radiative transfer in combustion systems", Commun. Num. Meth. Eng., 24:2, (2006), 85-96. [2] R. Pinnau, G. Thommes, “Optimal boundary control of glass cooling processes", Math. Methods Appl. Sci., 27:11, (2004), 1261-1281. [3] M. F. Modest, “Radiative heat transfer", New York: Academic Press, 2003. [4] G. V. Grenkin, “Algorithm for solving the boundary optimal control problem in a complex heat transfer model", Far Eastern Mathematical Journal, 16:1, (2016), 24-38. [5] G. V. Grenkin, A.Yu. Chebotarev, A. E. Kovtanyuk, N. D. Botkin, K.-H. Hoffmann, “Boundary optimal control problem of complex heat transfer model", J. Math. Anal. Appl., 433, (2016), 1243-1260. [6] A.Yu. Chebotarev, G.V. Grenkin, A.E Kovtanyuk, ”Unique solvability of a subdifferential boundary value problem for complex heat transfer equations", Far Eastern Mathematical Journal, 16:2, (2016), 229-236. [7] F. Hecht, “New development in FreeFem++", J. Num. Math., 20:3-4, (2012), 251-265. |