Tes-bo/UNet-CFD-FrameWork-cavity

This project trains a U-Net neural network to learn the mapping from boundary conditions (lid velocity and Reynolds number) to flow fields (pressure and velocity). The training data is generated automatically using OpenFOAM CFD simulations.

33
/ 100
Emerging

This project helps engineers and researchers quickly predict fluid flow patterns in a cavity. You provide basic conditions like the lid's speed and fluid properties (Reynolds number), and it rapidly outputs detailed pressure and velocity maps for the entire cavity. It's designed for anyone working with fluid dynamics who needs fast, approximate flow field simulations without waiting for traditional CFD computations.

Use this if you need to rapidly estimate pressure and velocity fields for cavity-driven flows based on boundary conditions, saving significant computational time compared to full CFD simulations.

Not ideal if you require highly precise, validated CFD results for critical engineering design or certification, or if your flow problem is not a cavity-driven flow.

fluid-dynamics computational-fluid-dynamics flow-prediction aerodynamics mechanical-engineering
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

C++

License

GPL-3.0

Last pushed

Jan 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tes-bo/UNet-CFD-FrameWork-cavity"

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