What is it about?
When air flows over an aircraft or spacecraft at high speeds, complex interactions occur between shockwaves (abrupt pressure changes) and the thin layer of air near the surface called the boundary layer. These shockwave-boundary layer interactions (SBLIs) can cause issues like increased drag, heat transfer, and unsteady loads. To better understand such complex flows , we developed a new approach to reconstruct the velocity field. We use an optical technique called background-oriented schlieren (BOS) to visualize density changes, then apply machine learning techniques in the form of physics-informed neural networks. These models incorporate knowledge of the governing flow equations to compute the full velocity field from just the BOS images.
Featured Image
Photo by Hermeus on Unsplash
Why is it important?
This work establishes a new way to gain deeper insights into supersonic flows by extracting quantitative information from simple visualizations. The approach could enable more efficient testing of high-speed vehicles to help engineers analyze and mitigate the adverse effects of SBLIs.
Read the Original
This page is a summary of: Assimilating mean velocity fields of a shockwave–boundary layer interaction from background-oriented schlieren measurements using physics-informed neural networks, Physics of Fluids, July 2024, American Institute of Physics,
DOI: 10.1063/5.0208040.
You can read the full text:
Contributors
The following have contributed to this page
