mediaTUM - Medien- und Publikationsserver

Titel:: Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations, Reduced Data Set (6.4k Samples)
Dokumenttyp:: Forschungsdaten
Verantwortlich:: Thuerey, Nils
Autorinnen / Autoren:: Thuerey, Nils; Xiangyu, Hu
Institutionszugehörigkeit:: TUM
Herausgeber:: TUM
Identifikator:: doi:10.14459/2018mp1470791
Enddatum der Datenerzeugung:: 05.10.2018
Fachgebiet:: DAT Datenverarbeitung, Informatik
Quellen der Daten:: Simulationen / simulations
Datentyp:: Datenbanken / data bases
Beschreibung:: This archive contains 6400 data sets of RANS simulations for the "Deep Flow Prediction" project, in addition to 90 test data sets. The data set is intended for training deep neural networks for fluid simulations.
Links:: Project & Source-Code
Schlagworte:: Fluid Simulation; Deep Learning; Navier-Stokes
Technische Hinweise:: Data format: numpy arrays, 128x128 with 6 channels: freestream x, freestream y, airfoil mask, output pressure, output velocity x, output velocity y.
View and download
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1470791):
rsync rsync://m1470791@dataserv.ub.tum.de/m1470791/
Sprache:: en
Rechte:: by-sa, http://creativecommons.org/licenses/by-sa/4.0
Horizon 2020:: ERC StG 637014

BibTeX

Vorkommen:

Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations, Reduced Data Set (6.4k Samples)