Physics-Informed Machine Learning for Hypersonic Turbulence

Turbulence modeling for compressible flow is essential for accurate modeling of heat transfer, skin friction, and pressure surrounding hypersonic vehicles to correctly predict vehicle survivability. High fidelity computational fluid dynamics (CFD) approaches are too computationally demanding and require faster, workhorse methods such as Reynolds Averaged Navier-Stokes (RANS) simulations for computation of flight trajectories and dynamics. However, current RANS turbulence closure models cannot accurately characterize hypersonic flowfield features. Physics-informed machine learning (PIML) methods provide an avenue for creation of more accurate turbulence models. In this STTR effort, Spectral Sciences, Inc. and Virginia Tech will develop an innovative PIML turbulence closure model leveraging recent advances in ensemble learning to enable efficient training with both experimental and high-fidelity simulation data in a unified data-driven framework.