Pattern Classification for GIS Base on GK Clustering Algorithm
Year: 2013
Type: article
Abstract: Four typical defects in GIS for PD detection are proposed, and the pulse, amplitude, phases, number of PD has been used to form the three-dimensional PQN matrix. Based on the PQN matrix, three two-dimensional distributions of Hqmax~Phi, Hqmean~Phi and Hn~Phi can be achieved. Then the new GK clustering method is introduced to separate the four different defects according to separate the four different partial discharge defects in gas in GIS, according to the parameters of Skewness (Sk), Kurtosis (Ku), number of peaks (Pe), cross-correlation factor (CC) and the discharge factor Q.
Source: Applied Mechanics and Materials
Authors: Hui Wang, Xiu Wei Li, Yu Xin Yun, Hai Yan Yuan
Institution: State Grid Shandong Electric Power Company (China)
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2018998346