Contribution to a conference proceedings/Contribution to a book

FZJ-2025-02454

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Drag Correlations for Multiphase Flows Using Artificial Neural Networks

Vorspohl, J. (Corresponding author) ; André, L. ; Rüttgers, M.FZJ* ; Schröder, W.

2025
Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag Jülich

This record in other databases:  

Please use a persistent id in citations: doi:10.34734/FZJ-2025-02454

Abstract: A novel approach for the generation of drag correlations for multiphase flows is presented. Fully resolved computational fluid dynamics simulations for multiphase flows are performed to provide ground truth data. An artificial neural network is trained to learn the accurate particle behavior based on less accurate flow data from the Lagrangian particle simulation. For the case of a settling sphericalparticle, this approach outperforms the existing empirical model.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. DFG project G:(GEPRIS)510921053 - FOR 5595: Öl-Kältemittel-Mehrphasenströmungen in Spalten mit bewegten Berandungen – Neuartige mikroskopische und makroskopische Ansätze für Experiment, Modellierung und Simulation (510921053) (510921053)

Appears in the scientific report 2025

---

Database coverage:

---