Saved in:
Bibliographic Details
Main Authors: Nohra, Michel, Dufour, Steven
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.05371
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917661864099840
author Nohra, Michel
Dufour, Steven
author_facet Nohra, Michel
Dufour, Steven
contents Multi-fluid flows are found in various industrial processes, including metal injection molding and 3D printing. The accuracy of multi-fluid flow modeling is determined by how well interfaces and capillary forces are represented. In this paper, the multi-fluid flow problem is discretized using a combination of a Physics-Informed Neural Network (PINN) with a finite element discretization. To determine the best PINN formulation, a comparative study is conducted using a manufactured solution. We compare interface reinitialization methods to determine the most suitable approach for our discretization strategy. We devise a neural network architecture that better handles complex free surface topologies. Finally, the coupled numerical strategy is used to model a rising bubble problem.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
Nohra, Michel
Dufour, Steven
Numerical Analysis
Multi-fluid flows are found in various industrial processes, including metal injection molding and 3D printing. The accuracy of multi-fluid flow modeling is determined by how well interfaces and capillary forces are represented. In this paper, the multi-fluid flow problem is discretized using a combination of a Physics-Informed Neural Network (PINN) with a finite element discretization. To determine the best PINN formulation, a comparative study is conducted using a manufactured solution. We compare interface reinitialization methods to determine the most suitable approach for our discretization strategy. We devise a neural network architecture that better handles complex free surface topologies. Finally, the coupled numerical strategy is used to model a rising bubble problem.
title Coupling of the Finite Element Method with Physics Informed Neural Networks for the Multi-Fluid Flow Problem
topic Numerical Analysis
url https://arxiv.org/abs/2405.05371