Fractional Feature Extraction and Pattern Recognition of Transformer Partial Discharge Sources

DOI

10.2991/iccsee.2013.167How to use a DOI?

Keywords

transformer, partial discharge, feature extraction, recognition

Abstract

The recognition of transformer partial discharge patterns is helpful for evaluating insulation condition of transformers.Six typical kinds of partial discharge patterns are tested in the study.Based on the characteristics of the data,the partial discharge patterns were divided into several classes. Thus the pattern recognition can be translated into a two category process,in which the recognition can be realized gradually.By analyzing the data,the characteristic parameters are found for recognizing the classes.Then use the confidence interval method to realize the recognition process, and the accuracy of this method was verified.The results show that the method is reliable for the partial discharge pattern recognition.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Guo-qiang Wang
AU  - Yong-li Zhu
AU  - Li-peng Liu
PY  - 2013/03
DA  - 2013/03
TI  - Fractional Feature Extraction and Pattern Recognition of Transformer Partial Discharge Sources
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 657
EP  - 661
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.167
DO  - 10.2991/iccsee.2013.167
ID  - Wang2013/03
ER  -