beingujjwalraj/Multiscale-Modelling-of-Material-Using-Machine-Learning

This repository demonstrates multiscale modeling of copper heat pipes using machine learning, integrating grain-scale data with FEA via a UMAT. It highlights grain size’s impact on stress, strain, and heat transfer for optimized material design.

28
/ 100
Experimental

This project helps material scientists and engineers understand how tiny grain sizes in materials like copper heat pipes affect their overall strength and heat transfer properties. It takes detailed, grain-level material data and uses machine learning to predict how a larger component will behave, giving you insights into optimizing material designs for better performance. The output is a more accurate simulation of how materials respond to stress and heat, considering their microstructure.

No commits in the last 6 months.

Use this if you need to integrate microstructural details like grain size into your finite element analysis (FEA) to improve predictions of material strength, stress distribution, and thermal performance.

Not ideal if your primary goal is general-purpose machine learning model development or if you're not working with material science, multiscale modeling, or FEA.

material-science finite-element-analysis heat-exchanger-design microstructure-engineering materials-characterization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

8

Forks

6

Language

Jupyter Notebook

License

Last pushed

Dec 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/beingujjwalraj/Multiscale-Modelling-of-Material-Using-Machine-Learning"

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