• DocumentCode
    1684611
  • Title

    The application of intelligent systems in power transformer design

  • Author

    Geromel, L.H. ; Souza, C.R.

  • Author_Institution
    CEFET/PR, Sao Paulo
  • Volume
    2
  • fYear
    2002
  • fDate
    6/24/1905 12:00:00 AM
  • Firstpage
    1504
  • Lastpage
    1509
  • Abstract
    The large number of variables and the fact that, in addition, their multiple interrelations are not completely known make power transformer design a quite involved task. This paper presents a novel power transformer design methodology using artificial neural networks (ANNs). The methodology described allows the application of an ANN in certain specific stages of the design. The expectation is that this work will contribute to the simplification of the design procedure. This novel methodology is also an important tool, not only for optimizing projects but also for substantially minimizing the necessary time for their execution. A database that contains the test results of 300 power transformers is used for the validation of the method. The results of the application of this methodology are presented and discussed
  • Keywords
    neural nets; optimisation; power system CAD; power transformers; artificial neural networks; database; design procedure simplification; intelligent systems; power transformer design methodology; project execution time minimization; project optimization; unknown variable interrelations; Artificial neural networks; Costs; Design methodology; Intelligent systems; Optimization methods; Power system protection; Power transformer insulation; Power transformers; Production; Temperature;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
  • Conference_Location
    Honolulu, HI
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7278-6
  • Type

    conf

  • DOI
    10.1109/IJCNN.2002.1007740
  • Filename
    1007740