SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.14339 · 2020

Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 13 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
tum-pbs/dl-surrogates pwc_unofficial 13 of 14
FunctionStatusWhere it lives
blockUNet Ran tum-pbs/dl-surrogates/shape-opt/train/DfpNet.py
code served (permissive licence) · get_code("999d2f1fb6b19f00")
calculateDragLift Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/DesignLoss_old.py
code served (permissive licence) · get_code("acef023df4ba28ae")
calculateDragLift_visc Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/DesignLoss_old.py
code served (permissive licence) · get_code("deed4c731756227f")
calculateDragLift_visc_phi Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/DesignLoss_modified.py
code served (permissive licence) · get_code("35e05cd5fa46231b")
combination Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/Helper.py
code served (permissive licence) · get_code("faf9a9731267b8a0")
convertSecond Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/Helper.py
code served (permissive licence) · get_code("33c9e18b87b1f5b1")
convert_center Ran tum-pbs/dl-surrogates/StructuredGrid/HicksHenne.py
code served (permissive licence) · get_code("c137336f222b6fc2")
extractGradients Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/VisualizationTools.py
code served (permissive licence) · get_code("78ff447217824e3d")
hickshenne Ran tum-pbs/dl-surrogates/StructuredGrid/HicksHenne.py
code served (permissive licence) · get_code("4a1a0948e80b7306")
pascalsTriangle Ran tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/Helper.py
code served (permissive licence) · get_code("3f5fd0a1b243a75b")
q_convert_point Ran tum-pbs/dl-surrogates/StructuredGrid/HicksHenne.py
code served (permissive licence) · get_code("f9731271f9ae4551")
torch_Dirac_delta Ran tum-pbs/dl-surrogates/shape-opt/levelset/Binarizer.py
code served (permissive licence) · get_code("4a73fd5d0c8a81ee")
torch_Heaviside Ran tum-pbs/dl-surrogates/shape-opt/levelset/Binarizer.py
code served (permissive licence) · get_code("3173ecca0c6c2913")
calculateDragLift_phi Not yet run tum-pbs/dl-surrogates/shape-opt/airfoil_optimizer/DesignLoss_modified.py
code served (permissive licence) · get_code("7583a129310a13bd")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Efficiently predicting the flowfield and load in aerodynamic shape optimisation remains a highly challenging and relevant task. Deep learning methods have been of particular interest for such problems, due to their success for solving inverse problems in other fields. In the present study, U-net based deep neural network (DNN) models are trained with high-fidelity datasets to infer flow fields, and then employed as surrogate models to carry out the shape optimisation problem, i.e. to find a drag minimal profile with a fixed cross-section area subjected to a two-dimensional steady laminar flow. A level-set method as well as Bezier-curve method are used to parameterise the shape, while trained neural networks in conjunction with automatic differentiation are utilized to calculate the gradient flow in the optimisation framework. The optimised shapes and drag force values calculated from the flowfields predicted by DNN models agree well with reference data obtained via a Navier-Stokes solver and from the literature, which demonstrates that the DNN models are capable of predicting not only flowfield but also yield satisfactory aerodynamic forces. This is particularly promising as the DNNs were not specifically trained to infer aerodynamic forces. In conjunction with the fast runtime, the DNN-based optimisation framework shows promise for general aerodynamic design problems.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.14339")
get_code_for_paper("2009.14339")
have("2009.14339")

Connect an agent — have() is free.