TY - GEN
T1 - Stationary Flow Predictions Using Convolutional Neural Networks
AU - Eichinger, Matthias
AU - Heinlein, Alexander
AU - Klawonn, Axel
PY - 2021
Y1 - 2021
N2 - Computational Fluid Dynamics (CFD) simulations are a numerical tool to model and analyze the behavior of fluid flow. However, accurate simulations are generally very costly because they require high grid resolutions. In this paper, an alternative approach for computing flow predictions using Convolutional Neural Networks (CNNs) is described; in particular, a classical CNN as well as the U-Net architecture are used. First, the networks are trained in an expensive offline phase using flow fields computed by CFD simulations. Afterwards, the evaluation of the trained neural networks is very cheap. Here, the focus is on the dependence of the stationary flow in a channel on variations of the shape and the location of an obstacle. CNNs perform very well on validation data, where the averaged error for the best networks is below 3%. In addition to that, they also generalize very well to new data, with an averaged error below 10%.
AB - Computational Fluid Dynamics (CFD) simulations are a numerical tool to model and analyze the behavior of fluid flow. However, accurate simulations are generally very costly because they require high grid resolutions. In this paper, an alternative approach for computing flow predictions using Convolutional Neural Networks (CNNs) is described; in particular, a classical CNN as well as the U-Net architecture are used. First, the networks are trained in an expensive offline phase using flow fields computed by CFD simulations. Afterwards, the evaluation of the trained neural networks is very cheap. Here, the focus is on the dependence of the stationary flow in a channel on variations of the shape and the location of an obstacle. CNNs perform very well on validation data, where the averaged error for the best networks is below 3%. In addition to that, they also generalize very well to new data, with an averaged error below 10%.
UR - http://www.scopus.com/inward/record.url?scp=85106438976&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-55874-1_53
DO - 10.1007/978-3-030-55874-1_53
M3 - Conference contribution
AN - SCOPUS:85106438976
SN - 9783030558734
T3 - Lecture Notes in Computational Science and Engineering
SP - 541
EP - 549
BT - Numerical Mathematics and Advanced Applications, ENUMATH 2019 - European Conference
A2 - Vermolen, Fred J.
A2 - Vuik, Cornelis
PB - Springer
T2 - European Conference on Numerical Mathematics and Advanced Applications, ENUMATH 2019
Y2 - 30 September 2019 through 4 October 2019
ER -