Multi-Phase Dataset for Ti and Ti-6Al-4V

TL;DR

This paper provides comprehensive databases of atomic configurations for various phases of titanium and Ti-6Al-4V alloy, enabling the development of machine learning interatomic potentials for accurate phase behavior modeling.

Contribution

The authors created extensive DFT-based databases for Ti and Ti-6Al-4V phases and extended data reduction strategies, facilitating improved MLIP model training and validation.

Findings

Databases include energies, forces, stresses for multiple phases.

Validated MLIP models using GAP and ACE frameworks.

Provided benchmark protocols for model evaluation.

Abstract

Titanium and its alloys are technologically important materials that display a rich phase behaviour. In order to enable large-scale, realistic modelling of Ti and its alloys on the atomistic scale, Machine Learning Interatomic Potentials (MLIPs) are crucial, but rely on databases of atomic configurations. We report databases of such configurations that represent the {\alpha}, \b{eta}, {\omega} and liquid phases of Ti and the Ti-6Al-4V alloy, where we provide total energy, force and stress values evaluated by Density Functional Theory (DFT) using the PBE exchange-correlation functional. We have also leveraged and extended a data reduction strategy, via non-diagonal supercells, for the vibrational properties of Ti and sampling of atomic species within bulk crystalline data for Ti-6Al-4V. These configurations may be used to fit MLIP models that can accurately model the phase behaviour of Ti and Ti-6Al-4V across a broad range of thermodynamic conditions. To validate models, we assembled a set of benchmark protocols, which can be used to rapidly develop and evaluate MLIP models. We demonstrated the utility of our databases and validation tools by fitting models based on the Gaussian Approximation Potential (GAP) and Atomic Cluster Expansion (ACE) frameworks.