Loading...

Accurate power transformer PD pattern recognition via its model

Rostaminia, R ; Sharif University of Technology

733 Viewed
  1. Type of Document: Article
  2. DOI: 10.1049/iet-smt.2016.0075
  3. Publisher: Institution of Engineering and Technology
  4. Abstract:
  5. In this study, a transformer model is proposed to simulate the behaviour of a real transformer, under presence ofdifferent types of defects which contribute to partial discharge (PD) generation, as closely as possible. Five different typesof defects (scratch on winding insulation, bubble in oil, moisture in insulation paper, very small free metal particle intransformer tank and fixed sharp metal point on transformer tank) are implemented artificially into these transformermodels to investigate the resultant PD current signal magnitude and characteristics. Time-domain PD currentwaveforms are recorded on those transformer models which have one type of those defects. The resultant statisticalPD current wave shapes and texture features are extracted from these captured PD current signals. The principalcomponent analysis (PCA) is used to reduce the dimension of feature spaces which are required to develop the inputsfor the classifier. The principal components obtained through PCA are applied to the support vector machine classifier,as an input. The classification results indicate that the extracted texture features (using grey-level covariance matrix)preserve the best characteristics for separation of the related patterns of those five defect models, accurately
  6. Keywords:
  7. Covariance matrix ; Defects ; Machine components ; Oil filled transformers ; Paper ; Partial discharges ; Power transformers ; Tanks (containers) ; Classification results ; Insulation paper ; Principal components ; Support vector machine classifiers ; Transformer modeling ; Transformer models ; Transformer tanks ; Winding insulation ; Pattern recognition
  8. Source: IET Science, Measurement and Technology ; Volume 10, Issue 7 , 2016 , Pages 745-753 ; 17518822 (ISSN)
  9. URL: http://ieeexplore.ieee.org/document/7577956