User: Guest  Login
Document type:
Zeitschriftenaufsatz 
Author(s):
Ma, Hao; Zhang, Yu-xuan; Haidn, Oskar J.; Thuerey, Nils; Hu, Xiang-yu 
Title:
Supervised learning mixing characteristics of film cooling in a rocket combustor using convolutional neural networks 
Abstract:
Machine learning approach has been applied previously to physical problem such as complex fluid flows. This paper presents a method of using convolutional neural networks to directly predict the mixing characteristics between coolant film and combusted gas in a rocket combustion chamber. Based on a reference experiment, numerical solutions are obtained from Reynolds-Averaged Navier–Stokes simulation campaign and then interpolated into the rectangular target grids. A U-net architecture is modifie...    »
 
Keywords:
Combustion chamber; Convolutional neural network; Deep learning; Film cooling; Flow-field prediction 
Dewey Decimal Classification:
620 Ingenieurwissenschaften 
Journal title:
Acta Astronautica 
Year:
2020 
Journal volume:
175 
Pages contribution:
11-18 
Covered by:
Scopus 
Language:
en 
Publisher:
Elsevier BV 
E-ISSN:
0094-5765 
Accepted:
08.05.2020 
Date of publication:
01.10.2020 
TUM Institution:
Lehrstuhl für Aerodynamik und Strömungsmechanik