Hybridization of front tracking and level set for multiphase flow simulations: a machine learning approach

Ikroh Yoon , Jalel Chergui (1) , Damir Juric (2, 1) , Seungwon Shin (3)

1 LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
2 COMET - COuplages Multiphysiques Et Transferts - LISN
3 Hongik University

A machine learning (ML) based approach is proposed to hybridize two wellestablished methods for multiphase flow simulations: Front Tracking (FT) and the Level Set (LS) methods. Based on the geometric information of the Lagrangian marker elements which represents the phase interface in FT simulations, the distance function field, which is the key feature for describing the interface in LS simulations, is predicted using an ML model. The trained ML model is implemented in our conventional numerical framework, and we finally demonstrate that the FT-based interface representation can easily and immediately be switched to an LS-based representation whenever needed during the simulation period.

Keywords: Multiphase flow; Numerical simulation; Front tracking; Level set; Artificial intelligence; Machine learning

Domains: Fluids mechanics [physics.class-ph]; Machine Learning [cs.LG]; Modeling and Simulation

Ikroh Yoon, Jalel Chergui, Damir Juric, Seungwon Shin. Hybridization of front tracking and level set for multiphase flow simulations: a machine learning approach. Journal of Mechanical Science and Technology, 2023, 37 (10), ⟨10.1007/s12206-023-04⟩. ⟨hal-04161702⟩