Health & Environmental Research Online (HERO)


Print Feedback Export to File
7091770 
Journal Article 
Autonomous Classification of PD Sources within Three-phase 11 kV PILC Cables 
Hunter, JA; Lewin, PL; Hao, L; Walton, C; Michel, M; , 
2013 
1 
IEEE Transactions on Dielectrics and Electrical Insulation
ISSN: 1070-9878
EISSN: 1558-4135 
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 
PISCATAWAY 
2117-2124 
WOS:000328704700020 
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%.