Attribute selection for fault location recognition in transmission lines

After a severe disturbance due to an insulation failure in a transmission line, the precise fault location is a critical problem for the maintenance crew. In order to avoid further economical and social costs, fault diagnosis has to be performed as soon as possible. Fault diagnosis has been a major...

Full description

Saved in:
Bibliographic Details
Main Authors: de Souza, S.M., Alves da Suva, A.P., Lima, A.C.S.
Format: Conference Proceeding
Language:English
Subjects:
Costs
Fault diagnosis
Fault location
Feature Extraction
Impedance
Insulation
Pattern Recognition
Power generation economics
Power system analysis computing
Power system economics
Power transmission lines
Transient Analysis
Transmission lines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:After a severe disturbance due to an insulation failure in a transmission line, the precise fault location is a critical problem for the maintenance crew. In order to avoid further economical and social costs, fault diagnosis has to be performed as soon as possible. Fault diagnosis has been a major area of investigation among power system problems and intelligent system applications. Several approaches have been proposed for solving this problem. This paper advocates the application of support vector machines for mapping the relationship between electrical signals and fault locations in transmission lines. The significance of voltages and currents is analyzed using steady-state and electromagnetic transient information, i.e., two ways of feeding the fault location models are compared. The tests consider different operating and fault conditions, including different types of fault, a variety of fault impedances, fault angles, line loading, equivalent system impedances, and fault locations
ISSN:1932-5517
DOI:10.1109/PES.2006.1709133