High-entropy carbide (Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2)C mechanical properties prediction with the use of machine learning potential

Abstract

The six-component high-entropy carbide (HEC) (Ti0.2Zr0.2Hf0.2Nb0.2Ta0.2)C has been studied. The electronic structure was calculated by using the ab initio package VASP for a supercell with 512 atoms constructed by using special quasi-random structures. The artificial neural networks potential (ANN-potential) was obtained by deep machine learning. The quality of the ANN-potential was estimated by the value of the energies, forces, and virials standard deviations. The generated ANN-potential was used to analyze both a defect-free model of the specified alloy, with 4096 atoms, and for the first time a polycrystalline HEC model, with 4603 atoms, by using the LAMMPS classical molecular dynamics package. The simulation of uniaxial cell tension was carried out, the elasticity coefficients, the all-round compression modulus, the elasticity modulus, and Poisson’s ratio were determined. The obtained values are in good agreement with the experimental and calculated data, which indicates a good predictive ability of the generated ANN-potential.