Constraint-Aware Neural Networks for Riemann Problems

by   Jim Magiera, et al.

Neural networks are increasingly used in complex (data-driven) simulations as surrogates or for accelerating the computation of classical surrogates. In many applications physical constraints, such as mass or energy conservation, must be satisfied to obtain reliable results. However, standard machine learning algorithms are generally not tailored to respect such constraints. We propose two different strategies to generate constraint-aware neural networks. We test their performance in the context of front-capturing schemes for strongly nonlinear wave motion in compressible fluid flow. Precisely, in this context so-called Riemann problems have to be solved as surrogates. Their solution describes the local dynamics of the captured wave front in numerical simulations. Three model problems are considered: a cubic flux model problem, an isothermal two-phase flow model, and the Euler equations. We demonstrate that a decrease in the constraint deviation correlates with low discretization errors for all model problems, in addition to the structural advantage of fulfilling the constraint.


Physical Symmetries Embedded in Neural Networks

Neural networks are a central technique in machine learning. Recent year...

Solving Nonlinear Parabolic Equations by a Strongly Implicit Finite-Difference Scheme

We discuss the numerical solution of nonlinear parabolic partial differe...

Surrogate-data-enriched Physics-Aware Neural Networks

Neural networks can be used as surrogates for PDE models. They can be ma...

Accelerating Eulerian Fluid Simulation With Convolutional Networks

Efficient simulation of the Navier-Stokes equations for fluid flow is a ...

Phase-bounded finite element method for two-fluid incompressible flow systems

An understanding of the hydrodynamics of multiphase processes is essenti...

A novel pressure-free two-fluid model for one-dimensional incompressible multiphase flow

A novel pressure-free two-fluid model formulation is proposed for the si...

Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media

We present efficient deep learning techniques for approximating flow and...