Loading...

Identification of Conductive Particles in Transformer Oil Model using Partial Discharge Signal

Firuzi, Keyvan | 2014

819 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46219 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Vakilian, Mehdi
  7. Abstract:
  8. Transformer are one of the most important equipment in transmission and distribution network. Transformer unplanned outage have severe impacts on the continuity of power system operation and is also an irreparable economic harm to power network operators. To improve the reliability of transformers and to achieve an optimum operation cost, online condition monitoring is inevitbale. Information about the quality of the transformer insulation system is known as the best parameter to be monitored in transformer. Since partiale discharge (PD) signals are initiated long before the beginning of a severe damage, monitoring and its evaluation can be employed to warn the operator. Data mining on the PD signals extracts useful information from large volumes of measured data. Recognition the type of transformer isolation fault using PD signals and the appropriate feature extraction and classification method is performed.
    Safety of transformer insulation is determined by oil dielectric strength, and more specifically by the oil pollution level. Since one of the best methods to detect abnormalities inside the transformer insulation is based on PD measurement, to detecting the conductive particles inside the transformer insulating oil used the general process of recognition of PD. This prosess includes measurement, PD patterns capture, parameters extracting, categories based on information in the before made database and finally deciding and diagnosis. Identification the characteristics of the particles in transformer oil, such as: fixed or free of particles, shape, size and material using PD measurement signals and by applying data mining techniques to the recorded signals in the time domain is shown. And also by using optimal classifier system, identification accuracy and obtaining information from the particles in transformer oil is increased to 97 %.
  9. Keywords:
  10. Partial Discharge ; Wavelet Transform ; Principal Component Analysis (PCA) ; Feature Extraction ; Support Vector Machine (SVM) ; Ulta Wide Band (UWB)Measurement ; Support Vector Machine (SVM)Classifier

 Digital Object List

 Bookmark

No TOC