Transformer Fault Position Recognition Based on Probability Support Vector Machine

DOI

10.2991/emeit.2012.448How to use a DOI?

Keywords

transformer,fault recognition,fault position,SVM,posterior probability

Abstract

Based on posterior probability of support vector machine, the analysis of dissolved gases in oil and the data of electrical tests are used comprehensively to recognize internal fault positions of the power transformer. This method not only inherits the advantages of the support vector machine for small samples, strong generalization ability and so on, but also provides the fault information of the power transformer by the form of probability. The output results not only provide the breaking down probability of the inner winding, tap changer and leads, iron core, structure and magnetic shielding body, insulating barrier and other parts, but also express the degree of credibility of conclusions. It adapts to the uncertainty characteristics of the fault positions. After analysis of examples, the validity of the model is verified.

Copyright

© 2012, 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  - Song-bo Huang
AU  - Wei-min Zhao
AU  - Tao Zhang
AU  - Li-ping Sima
AU  - Bo Wang
PY  - 2012/09
DA  - 2012/09
TI  - Transformer Fault Position Recognition Based on Probability Support Vector Machine
BT  - Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)
PB  - Atlantis Press
SP  - 2020
EP  - 2023
SN  - 1951-6851
UR  - https://doi.org/10.2991/emeit.2012.448
DO  - 10.2991/emeit.2012.448
ID  - Huang2012/09
ER  -