PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Classification of transformer oil using self-organizing networks and bayesian neural networks

Identyfikatory
Warianty tytułu
Konferencja
II International Conference on Advances in Processing, Testing and Application of Dielectric Materials, 15-17 September, Wrocław 2004
Języki publikacji
EN
Abstrakty
EN
In this paper supervised and unsupervised neural networks have been applied. To help the inexperienced transformer oil analyst to make good diagnosis, by classifying the transformer oil in classes giving its dielectric and cooling state; a Bayesian network a self organization map and a competitive layer have been applied. They present a high quality of classification in generalization phase.
Twórcy
autor
  • University of Batna- Faculty of Engineering- Dept. of Electrical Engineering, L.S.P.I.E- Batna, Algeria
autor
  • Ecole Nationale Polytechnique- High Voltage Laboratory, BP 182 EL-Harrach, Algiers, Algeria
Bibliografia
  • [1] DUKARM J.J., Transformer oil analyst TM DGA rules and standards, Delta-X Research document, Victoria (BC), Canada, 1996.
  • [2] HOLST A., The use of Bayesian neural network model for classification tasks, PHD thesis 1997, Dept. of numerical analysis and computer science, Royal institute of technology, S-100 44 Stockholm, SWEDEN, ISBN 91-7153-645-0, TRITA-NA-P9708, ISSN 1101-2250.
  • [3] MOKHNACHE L., BOUBAKEUR A., NAIT SAID N., Comparison of Different Neural Networks Algorithms Used in the Diagnosis and thermal ageing prediction of Transformer Oil, Proc. Int. Conf. on systems, man & cybernetics IEEE-SMC, Oct. Hammamat, Tunisia 2002, SMCO2-REG-485.
  • [4] KOHONEN T., Self-organizing maps, SPRINGER Verglag, Berlin, 1995.
  • [5] OSSOWSKI S., SWEK K., KOHONEN T., Neural network for load forecasting in power system, XX KKTOIUE, 1997, Kolobrzeg.
  • [6] KARTALOPOULOS S.V., Understanding neural networks and fuzzy logic- basic concepts and applications, IEEE Press, ISBN 0-7803-1128-0, (1996) IEEE order number: PP559.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-BUS3-0005-0046
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.