Physics-informed neural networks for high-speed flows

• Published in: Computer methods in applied mechanics and engineering Vol. 360; p. 112789
• Main Authors: Mao, Zhiping, Jagtap, Ameya D., Karniadakis, George Em
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.03.2020; Elsevier BV
• Subjects: Boundary conditions; Conservation laws; Density; Discontinuity; Domains; Equations of state; Euler equations; Euler-Lagrange equation; Forward problem; Hidden fluid mechanics; High speed; Inverse problems; Machine learning; Neural networks; Numerical methods; Oblique shock waves; Parameter identification; Riemann problem; Schlieren photography; Velocity; Conservation laws; Riemann problem; 65M70; Neural networks; 74S25; Machine learning; Hidden fluid mechanics; Euler equations; 35L65
• ISSN: 0045-7825
• DOI: 10.1016/j.cma.2019.112789

In this work we investigate the possibility of using physics-informed neural networks (PINNs) to approximate the Euler equations that model high-speed aerodynamic flows. In particular, we solve both the forward and inverse problems in one-dimensional and two-dimensional domains. For the forward prob...