Discontinuity Computing using Physics-Informed Neural Network

TL;DR

This paper enhances physics-informed neural networks (PINNs) for better shock wave discontinuity simulation by locally weakening network expressions near discontinuities, leading to sharper and more accurate shock capturing.

Contribution

It introduces a gradient-weighting strategy in PINNs to improve their ability to simulate discontinuities, outperforming traditional shock-capturing methods.

Findings

Improved shock discontinuity capturing in Burgers and Euler equations.

PINN with gradient-weighting outperforms WENO-Z in numerical tests.

Sharp discontinuities are achieved with smooth interior regions.

Abstract

Simulating discontinuities is a long standing problem especially for shock waves with strong nonlinear feather. Despite being a promising method, the recently developed physics-informed neural network (PINN) is still weak for calculating discontinuities compared with traditional shock-capturing methods. In this paper, we intend to improve the shock-capturing ability of the PINN. The primary strategy of this work is to weaken the expression of the network near discontinuities by adding a gradient-weight into the governing equations locally at each residual point. This strategy allows the network to focus on training smooth parts of the solutions. Then, automatically affected by the compressible property near shock waves, a sharp discontinuity appears with wrong inside shock transition-points compressed into well-trained smooth regions as passive particles. We study the solutions of one-dimensional Burgers equation and one- and two-dimensional Euler equations. Compared with the traditional high-order WENO-Z method in numerical examples, the proposed method can substantially improve discontinuity computing.