tdavydze/MachineLearning-CFD-DEM

Runtime ANN drag prediction for CFDEM/OpenFOAM—trained on fine‑mesh data using fluid/particle velocities and void fraction—boosts coarse‑mesh CFD‑DEM fidelity

29
/ 100
Experimental

This project helps chemical engineers and process designers improve the accuracy of their coarse-mesh CFD-DEM simulations. It takes high-resolution simulation data and uses it to train an Artificial Neural Network, which then predicts drag forces more accurately during subsequent coarse-mesh simulations. The end-user is a CFD-DEM practitioner who wants to better model fluid-particle interactions in systems like fluidized beds or pneumatic transport.

No commits in the last 6 months.

Use this if you need to perform high-fidelity simulations of fluid-particle interactions using coarse meshes and want to improve the accuracy of drag force predictions beyond traditional empirical models.

Not ideal if you are working with very simple fluid-particle systems where standard empirical drag models like Di Felice or Koch-Hill are already sufficient.

fluid-particle-interactions CFD-DEM process-simulation chemical-engineering multiphase-flow
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

C

License

Last pushed

Jul 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tdavydze/MachineLearning-CFD-DEM"

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