Calculation of proper energy barriers for atomistic kinetic Monte Carlosimulations on rigid lattice with chemical and strain field long-rangeeffects using artificial neural networks

摘要

In this paper we take a few steps further in the development of an approach based on the use of anartificial neural network (ANN) to introduce long-range chemical effects and zero temperature relaxation (elastic strain) effects in a rigid lattice atomistic kinetic Monte Carlo (AKMC) model. TheANN is trained to predict the vacancy migration energies as calculated given an interatomic potential with the nudged elastic band method, as functions of the local atomic environment. Thekinetics of a single-vacancy migration is thus predicted as accurately as possible, within the limits of the given interatomic potential. The detailed procedure to apply this method is described andanalyzed in detail. A novel ANN training algorithm is proposed to deal with the necessarily largenumber of input variables to be taken into account in the mathematical regression of the migration energies. The application of the ANN-based AKMC method to the simulation of a thermal annealing experiment in Fe-20%Cr alloy is reported. The results obtained are found to be in better agreementwith experiments, as compared to already published simulations, where no atomic relaxation was taken into account and chemical effects were only heuristically allowed for.