Machine-learning potentials for nanoscale simulations of deformation and fracture: example of TiB$_2$ ceramic

TL;DR

This paper develops machine-learning interatomic potentials for simulating the mechanical behavior and fracture of TiB₂ ceramics at the nanoscale, enabling accurate predictions of failure mechanisms and material properties beyond traditional ab initio methods.

Contribution

It introduces a strategy for fitting MLIPs suitable for nanoscale deformation and fracture simulations of ceramics, including transferability assessments to other conditions and phases.

Findings

MLIP accurately reproduces ab initio stresses and failure mechanisms.

Up-fitting MLIP extends applicability to larger systems and different loading conditions.

Transferability tests show potential for broader simulation use cases.

Abstract

Machine-learning interatomic potentials (MLIPs) offer a powerful avenue for simulations beyond length and timescales of ab initio methods. Their development for investigation of mechanical properties and fracture, however, is far from trivial since extended defects -- governing plasticity and crack nucleation in most materials -- are too large to be included in the training set. Using TiB$_2$ as a model ceramic material, we propose a strategy for fitting MLIPs suitable to simulate mechanical response of monocrystals until fracture. Our MLIP accurately reproduces ab initio stresses and failure mechanisms during room-temperature uniaxial tensile deformation of TiB$_2$ at the atomic scale ($\approx{10}^3$ atoms). More realistic tensile tests (low strain rate, Poisson's contraction) at the nanoscale ($\approx{10}^4$--10$^6$ atoms) require MLIP up-fitting, i.e. learning from additional ab initio configurations. Consequently, we elucidate trends in theoretical strength, toughness, and crack initiation patterns under different loading directions. To identify useful environments for further up-fitting, i.e., making the MLIP applicable to a wider spectrum of simulations, we asses transferability to other deformation conditions and phases not explicitly trained on.