Consistent and symmetry preserving data-driven interface reconstruction for the level-set method
This work addresses accuracy and symmetry issues in two-phase flow simulations, representing an incremental improvement over existing data-driven methods.
The authors tackled the problem of inaccurate interface reconstruction in the level-set method for computational fluid dynamics by proposing a combined model that uses a neural network for coarse resolutions and conventional methods for fine ones, achieving first-order convergence and preserving symmetry.
Recently, machine learning has been used to substitute parts of conventional computational fluid dynamics, e.g. the cell-face reconstruction in finite-volume solvers or the curvature computation in the Volume-of-Fluid (VOF) method. The latter showed improvements in terms of accuracy for coarsely resolved interfaces, however at the expense of convergence and symmetry. In this work, a combined approach is proposed, adressing the aforementioned shortcomings. We focus on interface reconstruction (IR) in the level-set method, i.e. the computation of the volume fraction and apertures. The combined model consists of a classification neural network, that chooses between the conventional (linear) IR and the neural network IR depending on the local interface resolution. The proposed approach improves accuracy for coarsely resolved interfaces and recovers the conventional IR for high resolutions, yielding first order overall convergence. Symmetry is preserved by mirroring and rotating the input level-set grid and subsequently averaging the predictions. The combined model is implemented into a CFD solver and demonstrated for two-phase flows. Furthermore, we provide details of floating point symmetric implementation and computational efficiency.