电路引用Partial discharge classification using principal component analysis combined with self-organizing map.pdfVIP

Partial Discharge Classification Using Principal Component Analysis Combined with Self-Organizing Map Norasage Pattanadech Phethai Nimsanong Electrical Engineering Dept, Faculty of Engineering Power System Operation and Control Section 2 King Mongkut’s Institute of Technology Ladkrabang Power System Control Dept, Metropolitan Bangkok, Thailand Electricity Authority, Bangkok, Thailand norasage@ phethai.ni@ Abstract—This document proposes a statistical classification can be also detected from electromagnetic wave in the range model using principal component analysis (PCA) for a data of very high frequency (VHF) or ultra high frequency (UHF). reduction approach combined with self-organizing map (SOM) This paper proposes a statistical classification model for for a classification purpose, so called, PCA-SOM model prediction of PD patterns obtained from the UHF compared with SOM model to classify partial discharge pattern measurement. Principal component analysis (PCA) was (PD) into four categories listed as corona at high voltage side, corona at low voltage side, surface discharge, and internal employed to reduce the number of original statistic variables discharge. PD signals were investigated by using ultra high and created the new independe