PCA based protection algorithm for transformer internal faults

Creative Commons License

Kılıç E., Özgönenel O., Usta Ö., Thomas D.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.17, sa.2, ss.125-142, 2009 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 17 Sayı: 2
  • Basım Tarihi: 2009
  • Doi Numarası: 10.3906/elk-0810-4
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.125-142
  • Anahtar Kelimeler: Protection, internal faults, transformers, PCA, ANN, RBF
  • Ondokuz Mayıs Üniversitesi Adresli: Evet

Özet

In this paper a new protection scheme is introduced to detect and identify transformer winding faults. The new approach is based on artificial neural networks (ANNs) using radial basis functions (RBFs) and the principal component analysis (PCA). The nonlinear system's input and output data is manipulated without considering any model of the system. This approach is used to detect and identify internal short circuit faults of a three phase custom built transformer. The suggested technique is also able to distinguish between the fault and magnetizing inrush current. The test studies carried out shows that the proposed method leads to satisfactory results in terms of detecting and isolating parameter faults taking place in non-linear dynamical systems.