• DocumentCode
    815715
  • Title

    Determining an approximate finite element mesh density using neural network techniques

  • Author

    Dyck, D.N. ; Lowther, D.A. ; McFee, S.

  • Author_Institution
    Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
  • Volume
    28
  • Issue
    2
  • fYear
    1992
  • fDate
    3/1/1992 12:00:00 AM
  • Firstpage
    1767
  • Lastpage
    1770
  • Abstract
    A system is presented which uses a neural network to predetermine the mesh density for modeling a magnetic device with finite elements. The system `learns´ how to mesh from examples of ideal meshes. Once trained, the system computes the mesh density given the geometric and material descriptions of a device. A mesh based on this density information can be used as the initial mesh for an adaptive solver
  • Keywords
    finite element analysis; magnetic devices; neural nets; adaptive solver; density information; finite element mesh density; ideal meshes; magnetic device; material descriptions; neural network techniques; Computer networks; Feature extraction; Finite element methods; Humans; Iron; Magnetic analysis; Magnetic devices; Magnetic materials; Neural networks; Packaging;
  • fLanguage
    English
  • Journal_Title
    Magnetics, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9464
  • Type

    jour

  • DOI
    10.1109/20.124047
  • Filename
    124047