Adjoint vs Physics AI
Surrogate-based and adjoint-based wing optimisation, side by side on GPUs
Paper title Combining and Comparing Aerodynamic Shape Optimization Approaches on GPUs: Adjoint Methods and Physics AI
Paper doi.org
Optimises the shape of a swept-wing aircraft two ways: with a Physics AI surrogate that infers surface and volume fields for new geometries in seconds, and with a GPU-native discrete adjoint of the RANS equations that gives exact design gradients.
- Published
- AIAA SciTech Forum
Share on LinkedIn, X or Bluesky, or or .
Know related work that belongs here? Suggest a link
Something wrong on this page? Tell the editor