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

Tamon Nakano (1) , Michele Alessandro Bucci (2, 1) , Jean-Marc Gratien (3) , Thibault Faney (3) , Guillaume Charpiat (1)

1 TAU - TAckling the Underspecified
2 Safran Tech
3 IFPEN - IFP Energies nouvelles

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.

Mots clés: Graph neural network; interface reconstruction; VoF method

Domaines: Dynamique des Fluides [physics.flu-dyn]; Physique Numérique [physics.comp-ph]; Apprentissage [cs.LG]

Tamon Nakano, Michele Alessandro Bucci, Jean-Marc Gratien, Thibault Faney, Guillaume Charpiat. Machine learning model for gas-liquid interface reconstruction in CFD numerical simulations. 2022. ⟨hal-03721729⟩