tum-pbs/Diffusion-based-Flow-Prediction

Official implementation of the AIAA Journal paper "Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models"

35
/ 100
Emerging

This project helps aerospace engineers and fluid dynamicists predict how air flows around aircraft wings, even when simulation inputs have uncertainties. You provide simulation parameters like wing shape or angle of attack, and it generates a range of possible flow field solutions, highlighting the likely variations. This allows designers to understand the inherent uncertainty in their simulations.

No commits in the last 6 months.

Use this if you need to understand the full range of possible outcomes and the inherent uncertainties in your airfoil flow simulations, rather than just a single deterministic prediction.

Not ideal if you only need a single, deterministic prediction of flow fields without considering the variability or uncertainty in the results.

aerodynamics fluid dynamics computational fluid dynamics aircraft design flow simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

85

Forks

7

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tum-pbs/Diffusion-based-Flow-Prediction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.