Fault location in underground systems through optimum-path forest

Author

Souza, André N. ; Costa, Pedro Da, Jr. ; Silva, Paulo S da ; Ramos, Caio C O ; Papa, João P.

Author_Institution

Dept. of Electr. Eng., UNESP - Univ. Estadual Paulista, Sao Paulo, Brazil

fYear

2011

fDate

25-28 Sept. 2011

Firstpage

1

Lastpage

5

Abstract

In this paper we propose an accurate method for fault location in underground distribution systems by means of an Optimum-Path Forest (OPF) classifier. We applied the Time Domains Reflectometry method for signal acquisition, which was further analyzed by OPF and several other well known pattern recognition techniques. The results indicated that OPF and Support Vector Machines outperformed Artificial Neural Networks classifier. However, OPF has been much more efficient than all classifiers for training, and the second one faster for classification.

Keywords

neural nets; pattern classification; power distribution faults; power engineering computing; support vector machines; time-domain reflectometry; underground distribution systems; OPF classifier; artificial neural network classifier; fault location; optimum-path forest; optimum-path forest classifier; pattern recognition techniques; signal acquisition; support vector machines; time domain reflectometry method; underground distribution systems; Accuracy; Fault location; Power cables; Prototypes; Support vector machines; Training; Vegetation; Fault Location; Optimum-Path Forest; Pattern Recognition; Underground Systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent System Application to Power Systems (ISAP), 2011 16th International Conference on

Conference_Location

Hersonissos

Print_ISBN

978-1-4577-0807-7

Electronic_ISBN

978-1-4577-0808-4

Type

conf

DOI

10.1109/ISAP.2011.6082204

Filename

6082204