• DocumentCode
    1515342
  • Title

    Electromagnetic device performance identification using knowledge based neural networks

  • Author

    Dandurand, Frederic ; Lowther, David A.

  • Author_Institution
    Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
  • Volume
    35
  • Issue
    3
  • fYear
    1999
  • fDate
    5/1/1999 12:00:00 AM
  • Firstpage
    1817
  • Lastpage
    1820
  • Abstract
    A knowledge based artificial neural network which represents the design equations of an electromagnetic device is described. The network architecture is based on a rule set developed from a simple algebraic model of the device, The system is then revised by using numerical solutions as training sets to remove the assumptions built in by the algebraic system
  • Keywords
    CAD; electrical engineering computing; electromagnetic devices; knowledge based systems; learning (artificial intelligence); neural nets; computer simulation; design equations; electromagnetic device performance identification; knowledge based neural networks; network architecture; numerical solutions; training sets; Artificial neural networks; Electromagnetic devices; Equations; Linearity; Modems; Neural networks; Numerical analysis; Process design; Response surface methodology; Shape;
  • fLanguage
    English
  • Journal_Title
    Magnetics, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9464
  • Type

    jour

  • DOI
    10.1109/20.767385
  • Filename
    767385