Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Machine learning methods for development of data-driven turbulence models. / Yakovenko, Sergey N.; Razizadeh, Omid.
High-Energy Processes in Condensed Matter, HEPCM 2020: Proceedings of the XXVII Conference on High-Energy Processes in Condensed Matter, Dedicated to the 90th Anniversary of the Birth of RI Soloukhin. ред. / Vasily M. Fomin. American Institute of Physics Inc., 2020. 030065 (AIP Conference Proceedings; Том 2288).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Machine learning methods for development of data-driven turbulence models
AU - Yakovenko, Sergey N.
AU - Razizadeh, Omid
N1 - Funding Information: The present study is partly supported by Russian Foundation for Basic Research (Project No. 17-01-00332) and performed within the framework of the Program of Fundamental Scientific Research of the state academies of sciences in 2013-2020 (Project No. ȺȺȺȺ-Ⱥ17-117030610128-8). Publisher Copyright: © 2020 Author(s). Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/10/26
Y1 - 2020/10/26
N2 - The implementation of the machine learning methods of convolutional neural network combined with support vector machines to enhance RANS closure models is presented. The RANS models are not universal and accurate, however they are computationally affordable. Finding a way to improve the model predictability will be an advantage, and machine learning algorithms based on available high-fidelity data sets for canonical flow cases obtained from DNS and measurements can be helpful for this. The application of these algorithms for a fully-developed turbulent channel flow between parallel walls, with periodic hills and for other cases is considered.
AB - The implementation of the machine learning methods of convolutional neural network combined with support vector machines to enhance RANS closure models is presented. The RANS models are not universal and accurate, however they are computationally affordable. Finding a way to improve the model predictability will be an advantage, and machine learning algorithms based on available high-fidelity data sets for canonical flow cases obtained from DNS and measurements can be helpful for this. The application of these algorithms for a fully-developed turbulent channel flow between parallel walls, with periodic hills and for other cases is considered.
KW - SIMULATION
KW - FLOW
UR - http://www.scopus.com/inward/record.url?scp=85096722207&partnerID=8YFLogxK
U2 - 10.1063/5.0028572
DO - 10.1063/5.0028572
M3 - Conference contribution
AN - SCOPUS:85096722207
T3 - AIP Conference Proceedings
BT - High-Energy Processes in Condensed Matter, HEPCM 2020
A2 - Fomin, Vasily M.
PB - American Institute of Physics Inc.
T2 - 27th Conference on High-Energy Processes in Condensed Matter, HEPCM 2020
Y2 - 29 June 2020 through 3 July 2020
ER -
ID: 27123932