Loading...

Online Monitoring of Multi-source PD Signals in a Single-phase Transformer Model with IEC 60270 and RF Methods

Firuzi, Keyvan | 2019

844 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: Farsi
  3. Document No: 51647 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Vakilian, Mehdi
  7. Abstract:
  8. Transformers are the key component in power system transmission and distribution networks. Condition based maintenance will increase their expected life and online monitoring is essential to ensure operation reliability. In this work a new approach to transformer online monitoring is provided based on partial discharge (PD) measurement.Multi-source PD signal separated using time-frequency S transform (ST) that is applied to the PD signal waveforms. The resultant ST matrix is then converted to gray scale image from which high level features are extracted using Bag of Words (BoW). Gaussian mixture model (GMM) clustering is used to discover clusters in the feature space. For recognition of separated PD sources a database is developed by measurement carried out on transformer artificial defect models. It is shown that by using HOG-SVM method 99.3% accuracy can be achieved. This is hardly affected by various external factors. Conducted multi-source PD case studies is shown that introduced method for separation active source and HOG-SVM method has superior performance in separating and identifying active sources, under sub-PRPD pattern application.For multiple defects case, traditional clustering methods is applied for separation of active sources. However, such an approach is impractical for online real-time monitoring due to the very large data size. To solve this problem a new method using stream clustering is introduced. The method separates the active sources by processing the signal once it is captured, then only a synopsis of the discharge data is stored and the raw data is discarded. This method was first implemented using the information obtained from the IEC60270 measurement method and the advantages and disadvantages of this solution have been investigated.Radio Frequency (RF) method has been used to solve the problems encountered for the online monitoring system using the IEC 60270 measuring method. RF method has advantages over the IEC 60270 measurement method for online monitoring because of greater immunity against external interference. However, the lack of a well-defined and specific calibration relationship between these two methods is the main disadvantage of the RF method. Simultaneous measurements, made with these two methods, has been carried out on various transformer PD source models to investigate the main parameters that affect the relationship of results between these two methods. Simultaneous measurements of PD using IEC60270 and RF techniques are employed to explore new features that can be used to distinguish between internal PDs and external interference, as well as among different internal PD sources. It is shown with experimental case studies that the proposed method for online monitoring of transformers is very effective in distinguishing and identifying various PD sources without the requirement of large storage of data
  9. Keywords:
  10. Power Transformer ; Partial Discharge ; IEC 60270 Method ; Data Stream Clustering ; Radio Frequency Method ; Gaussian Mixture Modeling ; Words Bag Model ; Support Vector Machine (SVM)Classifier

 Digital Object List

 Bookmark

No TOC