Convolutional Neural Networks for Approximation of Blood Flow in Artificial Lungs

  • Blood flow in channels of varying diameters <500μm exhibits strong non-linear effects. Multiphase finite volume approaches are feasible, but still computationally costly. Here, the feasibility of applying convolutional neural networks for blood flow prediction in artificial lungs is investigated. Training targets are precomputed using an Eulerian two-phase approach. To match with experimental data, the interphase drag and lift, as well as intraphase shear-thinning are adapted. A recursively branching regression network and convolution/deconvolution networks with plain skip connections and densely connected skips are investigated. A priori knowledge is incorporated in the loss functional to prevent the network from learning non-physical solutions. Inference from neural networks is approximately six orders of magnitude faster than the classical finite volume approach. Even if resulting in comparably coarse flow fields, the neural network predictions can be used as close to convergence initial solutions greatly accelerating classical flow computations.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Clemens BirkenmaierORCiD, Lars KrenkelORCiDGND
DOI:https://doi.org/10.1007/978-3-030-79561-0_43
ISBN:978-3-030-79560-3
Parent Title (English):New Results in Numerical and Experimental Fluid Mechanics XIII: Contributions to the 22nd STAB/DGLR Symposium
Publisher:Springer International Publishing
Place of publication:Cham
Editor:Andreas Dillmann, Gerd Heller, Ewald Krämer, Claus Wagner
Document Type:conference proceeding (article)
Language:English
Year of first Publication:2021
Release Date:2022/02/17
Tag:Deep learning fluid mechanics; Multiphase blood flow
Issue:1. Auflage
First Page:451
Last Page:460
Andere Schriftenreihe:Notes on Numerical Fluid Mechanics and Multidisciplinary Design ; 151
Institutes:Fakultät Maschinenbau
Regensburg Center of Biomedical Engineering - RCBE
Regensburg Center of Health Sciences and Technology - RCHST
Fakultät Maschinenbau / Labor Biofluidmechanik
Begutachtungsstatus:peer-reviewed
research focus:Lebenswissenschaften und Ethik
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG