DocumentCode :
13162
Title :
Autonomous classification of PD sources within three-phase 11 kV PILC cables
Author :
Hunter, J.A. ; Lewin, P.L. ; Hao, Liangliang ; Walton, C. ; Michel, Mathieu
Author_Institution :
Tony Davies High Voltage Lab., Univ. of Southampton, Southampton, UK
Volume :
20
Issue :
6
fYear :
2013
fDate :
Dec-13
Firstpage :
2117
Lastpage :
2124
Abstract :
To allow utilities to fulfill self-imposed and regulative performance targets that apply to them, the demand for new tools to help judge the health of modern power distribution networks has increased. The analysis of partial discharge (PD) signals has been identified as a potential diagnostic tool for the condition monitoring of HV plant. In order to investigate the PD activity produced by a range of defects within three-phase paper insulated lead covered (PILC) distribution cable under rated conditions, an experiment has been developed. The experiment incorporates a commercially available on-line PD measurement system employing a high frequency current transformer (HFCT) to record PD data in a manner that is currently in operation in the UK. By replicating field conditions and using realistic hardware to collect experiment data, that any findings or analysis tools developed during this investigation are directly transferable to use in the field. Four defective cable samples, each containing different imperfections that are known to reduce in-service plant life have been fabricated and extensively PD tested. The raw experiment data was processed to produce a dataset containing a range of features from individual PD pulses including time, frequency and time-frequency information. This data was used to optimize and train several support vector machine (SVM) models to perform automated pulse classification. Four SVM models were tested using different combinations of pulse features to identify which characteristics were most effective at transferring source dependent information for classification. The results of the automated algorithm validated the approach returning a classification accuracy of 91.1%.
Keywords :
computerised monitoring; condition monitoring; current transformers; fault diagnosis; high-frequency transformers; high-voltage techniques; optimisation; paper; partial discharge measurement; power cable insulation; power distribution lines; power engineering computing; signal classification; support vector machines; time-frequency analysis; HFCT; HV plant; PD pulse; PILC distribution cable; SVM model; automated pulse classification; autonomous PD source classification; condition monitoring; defective cable sample; high frequency current transformer; online PD measurement system; optimization; paper insulated lead covered; partial discharge; potential diagnostic tool; power distribution network; source dependent information transfer; support vector machine; time-frequency information; voltage 11 kV; Joints; Partial discharges; Power cable insulation; Power cables; Testing; Time-frequency analysis; Partial discharges; condition monitoring; paper insulated lead covered cable; support vector machine;
fLanguage :
English
Journal_Title :
Dielectrics and Electrical Insulation, IEEE Transactions on
Publisher :
ieee
ISSN :
1070-9878
Type :
jour
DOI :
10.1109/TDEI.2013.6678860
Filename :
6678860
Link To Document :
بازگشت