Title :
Pd pattern recognition based on linear discriminant analysis for GIS
Author :
Li, Mengchao ; Liu, Xun ; Zhang, Xiaoxing
Author_Institution :
Shangqiu Power Supply Co., Shangqiu, China
Abstract :
The fault diagnosis of Gas Insulated Switchgear (GIS) partial discharge (PD) is significant for mastering the essence of defects within the GIS accurately and guiding its maintenance. This paper designed four kinds of GIS defection models. The GIS gray intensity images were constructed based on mass specimens gathered by the ultra-high frequency and high speeds systems. Aimed at the PD characteristics and its defections, a PCA-FDA method is put forward based on PD images. Firstly, the principal component analysis is employed to condense the dimension of PD images, then the optimal sets of statistically uncorrelated discriminant vectors are extracted, and the minimum distance classifier was constructed as classifier. The identified results showed that this method can effectively elevate the discrimination of the four kinds of defects in GIS PD.
Keywords :
gas insulated switchgear; partial discharges; pattern recognition; principal component analysis; GIS defection; GIS gray intensity images; PCA-FDA method; PD characteristics; PD images; fault diagnosis; gas insulated switchgear partial discharge; linear discriminant analysis; minimum distance classifier; pattern recognition; principal component analysis; statistically uncorrelated discriminant vectors; ultra high frequency system; Atmospheric modeling; Feature extraction; Geographic Information Systems; Metals; Partial discharges; Pattern recognition; Principal component analysis; GIS; Linear Discriminant Analysis; PD; pattern recognition; principal component analysis;
Conference_Titel :
High Voltage Engineering and Application (ICHVE), 2010 International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
978-1-4244-8283-2
DOI :
10.1109/ICHVE.2010.5640806
