Logo RUB
  • Institute
    • ICAMS
      • Mission
      • Structure
      • Members
      • Fellows
    • Departments & Research Groups
      • Atomistic Modelling and Simulation
      • Scale-Bridging Thermodynamic and Kinetic Simulation
      • Micromechanical and Macroscopic Modelling
      • Artificial Intelligence for Integrated Material Science
      • Computational Design of Functional Interfaces
      • Scale-Bridging Simulation of Functional Composites
      • Materials Informatics and Data Science
      • High-Performance Computing in Materials Science
    • Central Services
      • Coordination Office
      • IT
  • Research
    • Overview
    • Publications
    • Software and Data
    • Collaborative research
    • Research networks
    • Young enterprises
  • Teaching
    • Overview
    • Materialwissenschaft B.Sc.
    • Materials Science and Simulation M.Sc.
    • ICAMS Graduate School
    • Student Projects
  • News & Events
    • Overview
    • News
    • Seminars and Workshops
    • Conferences
  • Services
    • Overview
    • Contact
    • Open positions
    • Travel information
 
ICAMS
ICAMS
MENÜ
  • RUB-STARTSEITE
  • Institute
    • ICAMS
    • Departments & Research Groups
    • Central Services
  • Research
    • Overview
    • Publications
    • Software and Data
    • Collaborative research
    • Research networks
    • Young enterprises
  • Teaching
    • Overview
    • Materialwissenschaft B.Sc.
    • Materials Science and Simulation M.Sc.
    • ICAMS Graduate School
    • Student Projects
  • News & Events
    • Overview
    • News
    • Seminars and Workshops
    • Conferences
  • Services
    • Overview
    • Contact
    • Open positions
    • Travel information
Home » Research » Publications

Just another WordPress site - Ruhr-Universität Bochum

Machine learning for metallurgy II. A neural-network potential for magnesium

M. Stricker, B. Yin, E. Mak, W. Curtin

Physical Review Materials, 4, 103602, (2020)

DOI: 10.1103/PhysRevMaterials.4.103602

Download: BibTEX

Interatomic potentials are essential for studying fundamental mechanisms of deformation and failure in metals and alloys because the relevant defects (dislocations, cracks, etc.) are far above the scales accessible to first-principles studies. Existing potentials for non-fcc metals and nearly all alloys are, however, not sufficiently quantitative for many crucial phenomena. Here machine learning in the Behler-Parrinello neural-network framework is used to create a broadly applicable potential for pure hcp magnesium (Mg). Lightweight Mg and its alloys are technologically important while presenting a diverse range of slip systems and crystal surfaces relevant to both plasticity and fracture that present a significant challenge for any potential. The machine learning potential is trained on first-principles density-functional theory (DFT) computable metallurgically relevant properties and is then shown to well predict metallurgically crucial dislocation and crack structures and competing phenomena. Extensive comparisons to an existing very good modified embedded atom method potential are made. These results demonstrate that a single machine learning potential can represent the wide scope of phenomena required for metallurgical studies. The DFT database is openly available for use in any other machine learning method. The method is naturally extendable to alloys, which are necessary for engineering applications but where ductility and fracture are controlled by complex atomic-scale mechanisms that are not well predicted by existing potentials.

back
{"type":"article", "name":"m.stricker202010", "author":"M. Stricker and B. Yin and E. Mak and W. Curtin", "title":"Machine learning for metallurgy II. A neuralnetwork potential for magnesium", "journal":"Physical Review Materials", "volume":"4", "OPTnumber":"10", "OPTmonth":"10", "year":"2020", "OPTpages":"103602", "OPTnote":"", "OPTkey":"ductility; elastic deformation; elastic modulus; electronic structure; fracture; line defects; plastic deformation; plasticity; point defects; potential energy surfaces; stacking faults; twinning; elemental metals; surfaces; density functional theory; mac", "DOI":"10.1103/PhysRevMaterials.4.103602"}
Logo RUB
  • Open positions
  • Travel information
  • Imprint
  • Privacy Policy
  • Sitemap
Ruhr-Universität Bochum
Universitätsstraße 150
44801 Bochum

  • Open positions
  • Travel information
  • Imprint
  • Privacy Policy
  • Sitemap
Seitenanfang Kontrast N