elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Data-Driven Techniques to Enhance and Supplement Computational Fluid Dynamics Prediction Capabilities

Bekemeyer, Philipp and Jäckel, Florian and Grabe, Cornelia (2020) Data-Driven Techniques to Enhance and Supplement Computational Fluid Dynamics Prediction Capabilities. First International Workshop on the Application of Machine Learning Techniques to Computational Fluid Dynamics Simulations and Analysis, 25. Juni 2020, Frankfurt, Germany.

Full text not available from this repository.

Abstract

Computational fluid dynamics simulations and in particular Reynolds-averaged Navier-Stokes simulations are the backbone of modern aerodynamic analysis and have become a crucial part of aircraft design and analysis. However, when looking at load predictions or moving towards the borders of the flight envelope, existing numerical simulation capabilities are still limited in terms of accuracy, robustness and/or performance. Instead, adding more knowledge through data-driven techniques offers the possibility to tackle some of these weaknesses. Within this work, two different routes will be presented that are currently pursued to enhance and supplement numerical simulation capabilities through data-driven techniques. First, reduced order modeling is introduced in which either a deep neural network architecture or a manifold-learning technique which is combined with a residual minimization strategy are employed to rapidly predict aerodynamic responses throughout the flight envelope. An industrial-relevant aircraft test case is used to demonstrate the performance of the proposed methods. Secondly, an insight into ongoing work on data-driven turbulence modeling is given. The herein presented approach concentrates on the structural uncertainty of the turbulence model transport equations and augments an existing model with a data-based, machine-learned term. Besides a brief description also some demonstration results for an aerodynamically relevant test case are shown.

Item URL in elib:https://elib.dlr.de/136255/
Document Type:Conference or Workshop Item (Speech)
Title:Data-Driven Techniques to Enhance and Supplement Computational Fluid Dynamics Prediction Capabilities
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Bekemeyer, PhilippPhilipp.Bekemeyer (at) dlr.deUNSPECIFIED
Jäckel, FlorianFlorian.Jaeckel (at) dlr.deUNSPECIFIED
Grabe, Corneliacornelia.grabe (at) dlr.deUNSPECIFIED
Date:25 June 2020
Refereed publication:No
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Computational Fluid Dynamics, Physics-Informed Machine Learning, Data-Driven Turbulence Modelling, Deep Neural Networks
Event Title:First International Workshop on the Application of Machine Learning Techniques to Computational Fluid Dynamics Simulations and Analysis
Event Location:Frankfurt, Germany
Event Type:Workshop
Event Dates:25. Juni 2020
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:fixed-wing aircraft
DLR - Research area:Aeronautics
DLR - Program:L AR - Aircraft Research
DLR - Research theme (Project):L - VicToria (old)
Location: Braunschweig
Institutes and Institutions:Institute for Aerodynamics and Flow Technology > CASE, BS
Institute for Aerodynamics and Flow Technology > CASE, GO
Deposited By: Bekemeyer, Philipp
Deposited On:01 Oct 2020 14:40
Last Modified:01 Oct 2020 14:40

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.