Research on Substation Overheating Fault On-line Monitoring Based on Support Vector Machine

DOI

10.2991/icecee-15.2015.302How to use a DOI?

Keywords

Substation; overheating fault; On-line monitoring; Support Vector Classification

Abstract

As an important part of power transition, the safe operation of substation is of great significance. In this paper, according to the characteristics of the substation equipment overheating fault and the theory of mathematical model of support vector classifier, equipment overheating fault diagnosis mechanism is established. By using inner product kernel function, the method realizes nonlinear mapping to high dimension space. The algorithm completes feature space division through the optimal hyper plane. The method is not only simple, but also has well "robust". Take substation in power plant as example, we verified the powerful function of support vector classifier and it can complete the fault diagnosis of excellent. The algorithm can completely satisfy the requirement of the traction substation equipment overheating fault on-line monitoring.

Copyright

© 2015, 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  - Min Xu
AU  - Luona Hu
AU  - Jizhe Wang
PY  - 2015/06
DA  - 2015/06
TI  - Research on Substation Overheating Fault On-line Monitoring Based on Support Vector Machine
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 1610
EP  - 1613
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.302
DO  - 10.2991/icecee-15.2015.302
ID  - Xu2015/06
ER  -