Skip to content

This project explores the inverse design of copper alloys using machine learning models to predict alloy compositions that yield desired mechanical properties. The approach leverages a curated dataset of copper-based alloys and implements several generative models (i.e. CVAE, ALAE, CTGAN) to map alloy features to target properties.

Notifications You must be signed in to change notification settings

AniruthAnanth/CopperAlloyInverseDesign

Repository files navigation

Inverse Design of Copper Alloys

This project explores the inverse design of copper alloys using machine learning models to predict alloy compositions that yield desired mechanical properties. The approach leverages a curated dataset of copper-based alloys and implements several generative models (i.e. CVAE, ALAE, CTGAN) to map alloy features to target properties.

  • Proof of concept.
  • Dataset was modified to replace unknown character with "?"
Gorsse, Stephane; Gouné, Mohamed; LIN, Wei-Chih; Girard, Lionel (2023). Dataset of mechanical properties and electrical conductivity of copper-based alloys. figshare. Dataset. https://doi.org/10.6084/m9.figshare.23735373.v1

About

This project explores the inverse design of copper alloys using machine learning models to predict alloy compositions that yield desired mechanical properties. The approach leverages a curated dataset of copper-based alloys and implements several generative models (i.e. CVAE, ALAE, CTGAN) to map alloy features to target properties.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published