A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction
This is an incremental improvement for computational fluid dynamics researchers, offering a more efficient approach to multi-material flow simulation.
The paper tackles the simulation of multi-material flows in 3D by introducing a machine-learning-based Volume of Fluid method that computes flux fractions using a trained neural network without explicit interface reconstruction, achieving numerical convergence with a better rate than two reference schemes as mesh size decreases.
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.