Title :
Pattern recognition of partial discharge on generator stators by using model bars
Author :
Wang, Wei ; Wufeng Li ; Liu, Lin ; Li, C.R. ; Ding, Lijian ; Wang, Zezhong ; Jingchun Wang ; Cheng, Y.C.
Author_Institution :
North China Inst. of Electr. Power, Beijing, China
Abstract :
Partial discharge (PD) can indicate defects in insulation of generator stator windings. In this paper, some generator model bars were made and some typical PD phenomena in generator stator windings were simulated. PD tests were also tried to find the features of composite PD. The data obtained from the test were analyzed and the spectrums of different types of PD were plotted using statistical parameters to reveal the feature of different patterns of PD. A BP neural network was also used to recognize the PD patterns
Keywords :
backpropagation; electric generators; electric machine analysis computing; insulation testing; machine testing; neural nets; partial discharge measurement; pattern recognition; stators; BP neural network; generator stators; model bars; partial discharge; pattern recognition; statistical parameters; Bars; Condition monitoring; Delamination; Dielectrics and electrical insulation; Frequency; Neural networks; Partial discharges; Pattern recognition; Stator windings; Testing;
Conference_Titel :
Electrical Insulating Materials, 2001. (ISEIM 2001). Proceedings of 2001 International Symposium on
Conference_Location :
Himeji
Print_ISBN :
4-88686-053-2
DOI :
10.1109/ISEIM.2001.973782