期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2018
卷号：153
期号：4
页码：042046
DOI：10.1088/1755-1315/153/4/042046
语种：English
出版社：IOP Publishing
摘要：Partial discharge (PD) measurement is among the most important diagnostics methods of insulation systems in high voltage equipment, which makes it convenient to assess the insulation status. Partial discharge activities may stem from various defects, and correspondingly behave differently. Here, the PD patterns produced by 3 different laboratory models representing defects in High Voltage Circuit Breakers are recorded and analyzed. The research aimed at conducting PD tests with three apparatus including prefabricated defects. From the PD pattern data, statistical features were extracted and these features were reduced by linear discriminant Analysis (LDA). Adaptive neuro-fuzzy inference system (ANFIS) was used to train the fuzzy inference system (FIS).The trained FIS was then used to recognize the source of the PDs. Results show thatANFIS classification has a high success rate and highest average success rate at 110kV reaches 95.83%.
