Artificial intelligence applied to simulation of radiation damage in ferritic alloys

Roberto P. Domingos, Gennaro M. Cerchiara, Flyura Djurabekova, Lorenzo Malerba

    Research outputpeer-review

    Abstract

    Molecular dynamics (MD) is the only computational tool that, without any approximation, can be applied to study atomic level phenomena involving radiation produced point-defects and their evolution driven by mutual interaction. Kinetic Monte Carlo (KMC) is suitable to extend the timeframe of an atomic level simulation to simulate an irradiation process, but all mechanisms involved must be known in advance, e.g. from MD studies. The present work is an effort to integrate artificial intelligence (AI) techniques, essentially an artificial neural network (ANN) and a fuzzy logic system (FLS), in order to build an adaptive model capable of improving both the physical reliability and the computational efficiency of a KMC model fully parameterized on MD results.

    Original languageEnglish
    Title of host publicationApplied Artificial Intelligence
    Subtitle of host publicationProceedings of the 7th International FLINS Conference, FLINS 2006
    EditorsPierre D'Hondt, Etienne E. Kerre, Da Ruan, Martine De Cock, Mike Nachtegael, Paolo F. Fantoni
    Place of PublicationSingapore, Singapore
    PublisherWorld Scientific Publishing Co. Pte Ltd
    Pages883-890
    Number of pages8
    Volume1
    ISBN (Electronic)9789814478472
    ISBN (Print)9789812566904
    DOIs
    StatePublished - 2006
    Event2006 - 7th international FLINS conference on Fuzzy Logic and Intelligent technologies in Nuclear Science - Genova
    Duration: 29 Aug 200631 Aug 2006
    Conference number: FLINS2006

    Publication series

    NameApplied Artificial Intelligence - Proceedings of the 7th International FLINS Conference, FLINS 2006

    Conference

    Conference2006 - 7th international FLINS conference on Fuzzy Logic and Intelligent technologies in Nuclear Science
    Country/TerritoryItaly
    CityGenova
    Period2006-08-292006-08-31

    Funding

    This work is supported by the EC-funded FP6 Integrated Project PERFECT (Prediction of Irradiation Damage Effect in Reactor Components).

    FundersFunder number
    Euratom 6th Framework Program

      ASJC Scopus subject areas

      • Information Systems
      • Computational Theory and Mathematics
      • Nuclear and High Energy Physics

      Cite this