Fast fault diagnosis in power transformers using optimum-path forest

Trabalho apresentado em evento

Fecha

2012-10-01

Registro en:

INES 2012 - IEEE 16th International Conference on Intelligent Engineering Systems, Proceedings, p. 209-212.

http://hdl.handle.net/11449/73612

10.1109/INES.2012.6249832

2-s2.0-84866646528

8212775960494686

http://repositorioslatinoamericanos.uchile.cl/handle/2250/3922604

Autor

Universidade Estadual Paulista (Unesp)

Universidade de São Paulo (USP)

Institución

Universidade Paulista Júlio de Mesquita Filho (Brasil)

Resumen

In this paper we propose a fast and an accurate method for fault diagnosis in power transformers by means of Optimum-Path Forest (OPF) classifier. Since we applied Dissolved Gas Analysis (DGA), the samples have been labeled by IEEE/IEC standard, which was further analyzed by OPF and several other well known supervised pattern recognition techniques. The experiments have showed that OPF can achieve high recognition rates with low computational cost. © 2012 IEEE.

Materias

Computational costs

Dissolved gas analysis

Optimum-path forests

Recognition rates

Supervised pattern recognition

Mostrar el registro completo del ítem