A model hierarchy for predicting the flow in stirred tanks with physics-informed neural networks

This paper explores the potential of Physics-Informed Neural Networks (PINNs) to serve as Reduced Order Models (ROMs) for simulating the flow field within stirred tank reactors (STRs). We solve the two-dimensional stationary Navier-Stokes equations within a geometrically intricate domain and explore...

Full description

Bibliographic Details

Published in:	Advances in Computational Science and Engineering Vol. 2; no. 2; pp. 91 - 129
Main Authors:	Trávníková, Veronika, Wolff, Daniel, Dirkes, Nico, Elgeti, Stefanie, von Lieres, Eric, Behr, Marek
Format:	Journal Article
Language:	English
Published:	01.06.2024
Subjects:	stirred tank reactors domain decomposition Physics-informed neural networks reduced order modeling Navier-Stokes equations
ISSN:	2837-1739, 2837-1739
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!