Eichinger, Matthias, Heinlein, Alexander ORCID: 0000-0003-1578-8104 and Klawonn, Axel ORCID: 0000-0003-4765-7387 (2019). Stationary flow predictions using convolutional neural networks. Technical Report.


Download (1MB) | Preview


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%.

Item Type: Preprints, Working Papers or Reports (Technical Report)
CreatorsEmailORCIDORCID Put Code
Eichinger, Matthiaseichingm@smail.uni-koeln.deUNSPECIFIEDUNSPECIFIED
Heinlein, Alexanderalexander.heinlein@uni-koeln.deorcid.org/0000-0003-1578-8104UNSPECIFIED
Klawonn, Axelaxel.klawonn@uni-koeln.deorcid.org/0000-0003-4765-7387UNSPECIFIED
URN: urn:nbn:de:hbz:38-104409
Series Name at the University of Cologne: Technical report series. Center for Data and Simulation Science
Volume: 2019,20
Date: 16 December 2019
Language: English
Faculty: Central Institutions / Interdisciplinary Research Centers
Divisions: Weitere Institute, Arbeits- und Forschungsgruppen > Center for Data and Simulation Science (CDS)
Subjects: Natural sciences and mathematics
Technology (Applied sciences)
Uncontrolled Keywords:
computational fluid dynamicsEnglish
machine learningEnglish
convolutional neural networksEnglish
URI: http://kups.ub.uni-koeln.de/id/eprint/10440


Downloads per month over past year


Actions (login required)

View Item View Item