Pd pattern recognition based on linear discriminant analysis for GIS

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.