Development of Artificial Neural Networks with Integrated Conditional Random Fields Capable of Predicting Non-linear Dynamics of the Flow Around Cylinders

Herzog, Sebastian and Wagner, Claus (2020) Development of Artificial Neural Networks with Integrated Conditional Random Fields Capable of Predicting Non-linear Dynamics of the Flow Around Cylinders. In: 21st STAB/DGLR Symposium on New Results in Numerical and Experimental Fluid Mechanics, 142, pp. 71-79. Springer Nature. 21. STAB/DGLR Symposium 2018, 6.-7. Nov. 2018, Darmstadt, Deutschland. doi: 10.1007/978-3-030-25253-3_7. ISBN 978-3-030-25252-6. ISSN 1612-2909.

Full text not available from this repository.

Official URL: https://doi.org/10.1007/978-3-030-25253-3_7

Abstract

This paper presents a new approach intended to predict flow dynamics based on observed data. The approach uses artificial neural networks extended by an adapted conditional random field. This artificial neural network is trained end-to-end and the embedded conditional random field memorizes previous events and uses this memory for flow predictions. The prediction capability of the proposed method is demonstrated for flows around cylinders which are computed with a Lattice Boltzmann method in order to train the artificial neural network.

Item URL in elib:

https://elib.dlr.de/135609/

Document Type:

Conference or Workshop Item (Speech)

Additional Information:

Print ISBN 978-3-030-25252-6 Online ISBN 978-3-030-25253-3 ISSN-electronic 1860-0824

Title:

Development of Artificial Neural Networks with Integrated Conditional Random Fields Capable of Predicting Non-linear Dynamics of the Flow Around Cylinders

Authors:

Authors	Institution or Email of Authors	Author's ORCID iD	ORCID Put Code
Herzog, Sebastian	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Wagner, Claus	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED

Date:

2020

Journal or Publication Title:

21st STAB/DGLR Symposium on New Results in Numerical and Experimental Fluid Mechanics

Refereed publication:

Yes

Open Access:

Gold Open Access:

In SCOPUS:

Yes

In ISI Web of Science:

Volume:

142

DOI:

10.1007/978-3-030-25253-3_7

Page Range:

pp. 71-79

Editors:

Editors	Email	Editor's ORCID iD	ORCID Put Code
Dillmann, Andreas	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Heller, Gerd	Airbus	UNSPECIFIED	UNSPECIFIED
Krämer, Ewald	Institut für Aerodynamik und Gasdynamik Universität Stuttgart	UNSPECIFIED	UNSPECIFIED
Wagner, Claus	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Tropea, Cameron	Fachgebiet Strömungslehre und Aerodynamik, TU Darmstadt	UNSPECIFIED	UNSPECIFIED
Jarkilic, Suad	TU Darmstadt	UNSPECIFIED	UNSPECIFIED

Publisher:

Springer Nature

Series Name:

Notes on Numerical Fluid Mechanics and Multidisciplinary Design

ISSN:

1612-2909

ISBN:

978-3-030-25252-6

Status:

Published

Keywords:

System modeling, Machine learning, ANNs

Event Title:

21. STAB/DGLR Symposium 2018

Event Location:

Darmstadt, Deutschland

Event Type:

international Conference

Event Dates:

6.-7. Nov. 2018

Organizer:

STAB/DGLR

HGF - Research field:

Aeronautics, Space and Transport

HGF - Program:

Transport

HGF - Program Themes:

Rail Transport

DLR - Research area:

Transport

DLR - Program:

V SC Schienenverkehr

DLR - Research theme (Project):

V - NGT BIT (old)

Location:

Göttingen

Institutes and Institutions:

Institute for Aerodynamics and Flow Technology > Ground Vehicles

Deposited By:

Wagner, Prof. Dr.-Ing. Claus

Deposited On:

05 Aug 2020 09:22

Last Modified:

05 Aug 2020 09:22

Repository Staff Only: item control page