Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations

TL;DR

This paper introduces a machine learning-enhanced volume of fluid method using Graph Neural Networks to improve interface reconstruction accuracy and efficiency in multi-phase flow simulations on unstructured meshes.

Contribution

It develops a GNN-based approach for interface reconstruction in VoF methods, addressing computational cost and accuracy issues on unstructured grids.

Findings

GNN model accelerates interface reconstruction process.

The method improves accuracy over traditional techniques.

Demonstrates potential for industrial multi-phase flow simulations.

Abstract

The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids. A major bottleneck of the VoF method is the interface reconstruction step due to its high computational cost and low accuracy on unstructured grids. We propose a machine learning enhanced VoF method based on Graph Neural Networks (GNN) to accelerate the interface reconstruction on general unstructured meshes. We first develop a methodology to generate a synthetic dataset based on paraboloid surfaces discretized on unstructured meshes. We then train a GNN based model and perform generalization tests. Our results demonstrate the efficiency of a GNN based approach for interface reconstruction in multi-phase flow simulations in the industrial context.