A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pintore, Moreno, Després, Bruno
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915374485733376
author Pintore, Moreno
Després, Bruno
author_facet Pintore, Moreno
Després, Bruno
contents We present a machine-learning based Volume Of Fluid method to simulate multi-material flows on three-dimensional domains. One of the novelties of the method is that the flux fraction is computed by evaluating a previously trained neural network and without explicitly reconstructing any local interface approximating the exact one. The network is trained on a purely synthetic dataset generated by randomly sampling numerous local interfaces and which can be adapted to improve the scheme on less regular interfaces when needed. Several strategies to ensure the efficiency of the method and the satisfaction of physical constraints and properties are suggested and formalized. Numerical results on the advection equation are provided to show the performance of the method. We observe numerical convergence as the size of the mesh tends to zero $h=1/N_h\searrow 0$, with a better rate than two reference schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction
Pintore, Moreno
Després, Bruno
Numerical Analysis
Machine Learning
35Q35, 68T07, 76-10, 76M12
We present a machine-learning based Volume Of Fluid method to simulate multi-material flows on three-dimensional domains. One of the novelties of the method is that the flux fraction is computed by evaluating a previously trained neural network and without explicitly reconstructing any local interface approximating the exact one. The network is trained on a purely synthetic dataset generated by randomly sampling numerous local interfaces and which can be adapted to improve the scheme on less regular interfaces when needed. Several strategies to ensure the efficiency of the method and the satisfaction of physical constraints and properties are suggested and formalized. Numerical results on the advection equation are provided to show the performance of the method. We observe numerical convergence as the size of the mesh tends to zero $h=1/N_h\searrow 0$, with a better rate than two reference schemes.
title A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction
topic Numerical Analysis
Machine Learning
35Q35, 68T07, 76-10, 76M12
url https://arxiv.org/abs/2507.05218