Artificial intelligence applied to atomistic kinetic Monte Carlo simulations in FeCu alloys

Research output: Contribution to journalArticle

Documents & links


Vacancy migration energies vs. the local atomic configuration (LAC) in FeCu alloys have been tabulated using an interatomic potential. Subsets of these tabulations have been used to train an artificial neural network (ANN) to predict all LAC-dependent vacancy migration energies. The error of the ANN has been evaluated by a fuzzy logic system, allowing a feedback to be introduced for further training. This artificial intelligence system is used to develop a novel approach to atomistic kinetic Monte Carlo simulations, aimed at providing a better description of the kinetic path followed by the system through diffusion of solute atoms in the alloy via vacancy mechanism. Fe-Cu has been chosen because of the importance of Cu precipitation in Fe for the embrittlement of reactor pressure vessels of existing nuclear power plants. Here the method is described in some detail and the first results of its application are presented and briefly discussed.


Original languageEnglish
Pages (from-to)8-12
JournalNuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms
Publication statusPublished - Jan 2007
Event2006 - COSIRES: computer Simulation of Radiation Effects in Solids - Pacific Northwest National Laboratory, Richland, United States
Duration: 18 Jun 200623 Jun 2006


  • kinetic Monte Carlo, artificial intelligence, neural network, fuzzy logic, iron-copper, vacancy migration energy

ID: 255092