NPLIC: A machine learning approach to piecewise linear interface construction

Abstract

Piecewise Linear Interface Construction (PLIC) is frequently used to geometrically reconstruct fluid interfaces in Computational Fluid Dynamics (CFD) modeling of two-phase flows. PLIC reconstructs interfaces from a scalar field that represents the volume fraction of each phase in each computational cell. Given the volume fraction and interface normal, the location of a linear interface is uniquely defined. For a cubic computational cell (3D), the position of the planar interface is determined by intersecting the cube with a plane, such that the volume of the resulting truncated polyhedron cell is equal to the volume fraction. Yet it is geometrically complex to find the exact position of the plane, and it involves calculations that can be a computational bottleneck of many CFD models. However, while the forward problem of 3D PLIC is challenging, the inverse problem, of finding the volume of the truncated polyhedron cell given a defined plane, is simple. In this work, we propose a deep learning model for the solution to the forward problem of PLIC by only making use of its inverse problem. The proposed model is up to several orders of magnitude faster than traditional schemes, which significantly reduces the computational bottleneck of PLIC in CFD simulations.

Analytic Solution to the Piecewise Linear Interface Construction Problem and Its Application in Curvature Calculation for Volume-of-Fluid Simulation Codes

“…By dividing N a by the execution time, we obtain the performance in TFLOPs/s (integer and bit operations are included since these are performed on the same CUDA cores as floating-point operations on Nvidia Pascal), showing that computing efficiency is not significantly impacted by the special functions used in the analytic solutions. It is noteworthy that there also is a novel neural network-based approach termed NPLIC that promises significant speedup, especially for more complex, non-cubic lattices [38]. This approach efficiently works on GPU hardware by using mainly multiplication and addition.…”

Development of an Improved One-Hot Encoding Method for Bubbly Flow Image Prediction Generation under Continuous Superficial Gas Velocities

“…Image processing method is one of the main means used for bubbly flow characteristic non-intrusive detection. Since traditional image processing methods rely heavily on manual adjustments, recently, several researchers have explored the use of deep learning to analyze bubbly flow images , and have improved the detection efficiency and accuracy greatly. However, deep learning algorithms require numerous high-quality bubbly flow images.…”

Error-Correcting Neural Networks for Two-Dimensional Curvature Computation in the Level-Set Method

“…The core of their system is a finite-volume flux function embodied in dense-layered neural models trained with lines, arcs, and corners. Another piece of contemporary work is due to Ataei et al [38]. They have proposed a neural piece-wise linear IR method as a way of circumventing the VOF difficulties to locate moving fronts.…”