Physics-informed neural networks for solving Reynolds-averaged Navierx2013Stokes equations

07/22/2021

∙

Physics-informed neural networks (PINNs) are successful machine-learning methods for the solution and identification of partial differential equations (PDEs). We employ PINNs for solving the Reynolds-averaged Navierx2013Stokes (RANS) equations for incompressible turbulent flows without any specific model or assumption for turbulence, and by taking only the data on the domain boundaries. We first show the applicability of PINNs for solving the Navierx2013Stokes equations for laminar flows by solving the Falknerx2013Skan boundary layer. We then apply PINNs for the simulation of four turbulent-flow cases, i.e., zero-pressure-gradient boundary layer, adverse-pressure-gradient boundary layer, and turbulent flows over a NACA4412 airfoil and the periodic hill. Our results show the excellent applicability of PINNs for laminar flows with strong pressure gradients, where predictions with less than 1 also obtain very good accuracy on simulation results even for the Reynolds-stress components.

READ FULL TEXT

Physics-informed neural networks for solving Reynolds-averaged Navierx2013Stokes equations

Learning Only On Boundaries: a Physics-Informed Neural operator for Solving Parametric Partial Differential Equations in Complex Geometries

Physics-Informed Boundary Integral Networks (PIBI-Nets): A Data-Driven Approach for Solving Partial Differential Equations

A Physics Informed Neural Network Approach to Solution and Identification of Biharmonic Equations of Elasticity

Error Estimates and Physics Informed Augmentation of Neural Networks for Thermally Coupled Incompressible Navier Stokes Equations

Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil

Open-source Framework for Transonic Boundary Layer Natural Transition Analysis over Complex Geometries in Nektar++

A New Magneto-Micropolar Boundary Layer Model for Liquid Flows – Effect of Micromagnetorotation (MMR)

Physics-informed neural networks for solving Reynolds-averaged Navierx2013Stokes equations

Related Research

Learning Only On Boundaries: a Physics-Informed Neural operator for Solving Parametric Partial Differential Equations in Complex Geometries

Physics-Informed Boundary Integral Networks (PIBI-Nets): A Data-Driven Approach for Solving Partial Differential Equations

A Physics Informed Neural Network Approach to Solution and Identification of Biharmonic Equations of Elasticity

Error Estimates and Physics Informed Augmentation of Neural Networks for Thermally Coupled Incompressible Navier Stokes Equations

Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil

Open-source Framework for Transonic Boundary Layer Natural Transition Analysis over Complex Geometries in Nektar++

A New Magneto-Micropolar Boundary Layer Model for Liquid Flows – Effect of Micromagnetorotation (MMR)