Physics-informed deep learning for incompressible laminar flows

A comparative study of the LBE and GKS methods for 2D near incompressible laminar flows

We compare the lattice Boltzmann equation (LBE) and the gas-kinetic scheme (GKS) applied to 2D incompressible laminar flows. Although both methods are derived from the Boltzmann equation thus share a common kinetic origin, numerically they are rather different. The LBE is a finite difference method, while the GKS is a finite-volume one. In addition, the LBE is valid for near incompressible flow...

The Incompressible Laminar Axisymmetric Wake

Development length of laminar magnetohydrodynamics pipe flows

In this article, a laminar magnetohydrodynamics (MHD) developing flow of an incompressible electrically conducting fluid subjected to an external magnetic field is considered. The aim of the study is to propose a correlation for computing the development length of the laminar MHD developing flow in a pipe. A numerical approach is considered to solve the problem. In the first step, the numerical...

Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations

We introduce physics informed neural networks – neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this second part of our two-part treatise, we focus on the problem of data-driven discovery of partial differential equations. Depending on whether the available data is sca...

Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations

We introduce physics informed neural networks – neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this two part treatise, we present our developments in the context of solving two main classes of problems: data-driven solution and data-driven discovery of partial differe...