TiAlNb alloy interatomic potentials: comparing passive and active machine learning techniques with MTP and DeePMD

Intermetallic titanium aluminides are interesting for aerospace and automotive applications due to their superior high-temperature mechanical properties. In particular, γ-TiAl-based alloys containing 5–10 at.% Niobium (Nb) have attracted significant attention. Molecular dynamics (MD) simulations can elucidate and optimize these materials, provided that accurate interatomic potentials are available. In this work, we compare active and passive machine learning approaches for developing TiAlNb interatomic potentials using both deep potential molecular dynamics (DeePMD) and the moment tensor potential (MTP) methods. Our comprehensive evaluation encompasses elastic constants, equilibrium volume, lattice parameters, and finite-temperature behavior, as well as simulated tension tests and generalized stacking fault energy calculations to assess the impact of Nb on the thermo-mechanical properties of γ-TiAl and α2-Ti3Al phases. Active learning consistently outperformed passive learning for both methods while requiring only a fraction of the training samples. Notably, active learning with DeePMD yielded a single potential capable of predicting the properties of both phases, whereas MTP exhibited limitations that necessitated separate training for each phase. Although active learning potentials excelled in predicting high-temperature behavior, their room-temperature property predictions were less accurate due to a sample selection bias toward higher temperatures. Overall, our thermomechanical analysis demonstrates that Nb incorporation enhances ductility while simultaneously reducing strength.

Subjects

TiAlNb alloy

machine-learning interatomic potentials

deep learning

moment tensor

active learning

molecular dynamics

density functional theory

DDC Class

620.11: Engineering Materials

006.3: Artificial Intelligence

660: Chemistry; Chemical Engineering

Publication version

publishedVersion

Lizenz

https://creativecommons.org/licenses/by/4.0/

Name

fmats-12-1591955-g008.tif

Size

574.11 KB

Format

TIFF

Name

DataSheet1.pdf

Size

3.51 MB

Format

Adobe PDF

Name

fmats-12-1591955-g006.tif

Size

611.51 KB

Format

TIFF

Name

fmats-12-1591955-g005.tif

Size

437.93 KB

Format

TIFF

Name

fmats-12-1591955-g001.tif

Size

577 KB

Format

TIFF

Name

fmats-12-1591955-g007.tif

Size

607.75 KB

Format

TIFF

Name

fmats-12-1591955.pdf

Size

45.28 MB

Format

Adobe PDF

Name

fmats-12-1591955-g004.tif

Size

524.59 KB

Format

TIFF

Name

fmats-12-1591955-g002.tif

Size

487.09 KB

Format

TIFF

Name

fmats-12-1591955-g003.tif

Size

519.54 KB

Format

TIFF

Options

TiAlNb alloy interatomic potentials: comparing passive and active machine learning techniques with MTP and DeePMD