SIAM Conference on Computational Science and Engineering 2023, Amsterdam, Hollanda, 27 Şubat - 03 Mart 2023
We introduce the application of physics-informed neural networks (PINN) for Boltzmann-BGK equations for nearly incompressible flows. The governing equations are discretized in the velocity space using Hermite polynomials, resulting in a first-order conservation law. A perfectly matching layer (PML) surrounding the computational domain is used to dampen the waves leaving the domain. A multi-domain approach is used with PINN to ensure the continuity of the solution. The damping profile of the PML is an output of the PINN offering a suitable constant for absorbing the waves.