Construction of an hybrid Artificial Neural Network - Fuzzy Logic system to perform Atomistic Kinetic Monte Carlo simulations in iron-copper alloys

Research output: ThesisMaster's thesis

Standard

Construction of an hybrid Artificial Neural Network - Fuzzy Logic system to perform Atomistic Kinetic Monte Carlo simulations in iron-copper alloys. / Castin, Nicolas; Djurabekova, Flyura (Peer reviewer).

Mol, Belgium : BNEN - Belgian Nuclear Higher Education Network, 2006. 100 p.

Research output: ThesisMaster's thesis

Bibtex - Download

@phdthesis{e2dbc890368e404a9e0d88359411b629,
title = "Construction of an hybrid Artificial Neural Network - Fuzzy Logic system to perform Atomistic Kinetic Monte Carlo simulations in iron-copper alloys",
abstract = "Neutron-irradiation enhanced copper precipitation in iron is one of the major causes of the shift in the ductile-to-brittle transition temperature in reactor pressure vessel steels. This process has been studied for years by computer simulation. Molecular dynamics is used to study atomic collision cascades induced by primary knock-on atoms, whereas Monte Carlo simulations are used to model thermal diffusion of created microscopic defects. This thesis aims at building an improved Atomistic Kinetic Monte Carlo (AKMC) simulation to study the thermal diffusion of vacancies and the induced copper precipitation. The vacancy migration energies are calculated with the aid of an Artificial Neural Network, trained with a limited set of Molecular Dynamics evaluated examples. A Fuzzy Logic feedback is constructed to reduce the mean error committed. The improved AKMC algorithm is validated and a series of AKMC simulations are performed to study the evolution of the copper solubility limit in iron with temperature.",
keywords = "artificial intelligence, atomistic computer simulation, iron-copper alloys",
author = "Nicolas Castin and Flyura Djurabekova",
note = "Score = 2",
year = "2006",
month = "8",
day = "31",
language = "English",
publisher = "BNEN - Belgian Nuclear Higher Education Network",
school = "BNEN - Belgian Nuclear Higher Education Network",

}

RIS - Download

TY - THES

T1 - Construction of an hybrid Artificial Neural Network - Fuzzy Logic system to perform Atomistic Kinetic Monte Carlo simulations in iron-copper alloys

AU - Castin, Nicolas

A2 - Djurabekova, Flyura

N1 - Score = 2

PY - 2006/8/31

Y1 - 2006/8/31

N2 - Neutron-irradiation enhanced copper precipitation in iron is one of the major causes of the shift in the ductile-to-brittle transition temperature in reactor pressure vessel steels. This process has been studied for years by computer simulation. Molecular dynamics is used to study atomic collision cascades induced by primary knock-on atoms, whereas Monte Carlo simulations are used to model thermal diffusion of created microscopic defects. This thesis aims at building an improved Atomistic Kinetic Monte Carlo (AKMC) simulation to study the thermal diffusion of vacancies and the induced copper precipitation. The vacancy migration energies are calculated with the aid of an Artificial Neural Network, trained with a limited set of Molecular Dynamics evaluated examples. A Fuzzy Logic feedback is constructed to reduce the mean error committed. The improved AKMC algorithm is validated and a series of AKMC simulations are performed to study the evolution of the copper solubility limit in iron with temperature.

AB - Neutron-irradiation enhanced copper precipitation in iron is one of the major causes of the shift in the ductile-to-brittle transition temperature in reactor pressure vessel steels. This process has been studied for years by computer simulation. Molecular dynamics is used to study atomic collision cascades induced by primary knock-on atoms, whereas Monte Carlo simulations are used to model thermal diffusion of created microscopic defects. This thesis aims at building an improved Atomistic Kinetic Monte Carlo (AKMC) simulation to study the thermal diffusion of vacancies and the induced copper precipitation. The vacancy migration energies are calculated with the aid of an Artificial Neural Network, trained with a limited set of Molecular Dynamics evaluated examples. A Fuzzy Logic feedback is constructed to reduce the mean error committed. The improved AKMC algorithm is validated and a series of AKMC simulations are performed to study the evolution of the copper solubility limit in iron with temperature.

KW - artificial intelligence

KW - atomistic computer simulation

KW - iron-copper alloys

UR - http://ecm.sckcen.be/OTCS/llisapi.dll/open/ezp_33134

M3 - Master's thesis

PB - BNEN - Belgian Nuclear Higher Education Network

CY - Mol, Belgium

ER -

ID: 100615