A highly transferable and efficient machine learning interatomic potentials study of α-Fe-C binary system

doi:10.1016/j.actamat.2024.120408

A highly transferable and efficient machine learning interatomic potentials study of α-Fe-C binary system

2024-12-01

1

OA

AI

DOI：10.1016/j.actamat.2024.120408

Original

Original request for help

Save

Abstract

En 中文

Machine learning interatomic potentials (MLIPs) for alpha-iron and carbon binary system have been constructed aiming for understanding the mechanical behavior of Fe-C steel and carbides. The MLIPs were trained using an extensive reference database produced by spin polarized density functional theory (DFT) calculations. The MLIPs reach the DFT accuracies in many important properties which are frequently engaged in Fe and Fe- C studies, including kinetics and thermodynamics of C in alpha-Fe with vacancy, grain boundary, and screw dislocation, and basic properties of cementite and cementite-ferrite interfaces. In conjunction with these MLIPs, the impact of C atoms on the mobility of screw dislocation at finite temperature, and the C-decorated core configuration of screw dislocation were investigated, and a uniaxial tensile test on a model with multiple types of defects was conducted.

Keywords:

Behler-Parrinello neural network potential

Deep potential

Iron

Carbon

Carbide

Molecular dynamics

DFT

A highly transferable and efficient machine learning interatomic potentials study of α-Fe-C binary system

Abstract

Journal

Organization