An investigative study on the influence of correlation of PD statistical features on PD pattern recognition

Abduallhi Abubaker Mas'ud, Brian G. Stewart

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)
30 Downloads (Pure)

Abstract

This paper investigates the influence of correlation coefficients of partial discharge (PD) statistical fingerprints on the classification performance of the ensemble neural network (ENN). PD measurements were carried out according to the IEC 60270 standard. Independent statistical parameters of skewness, kurtosis, cross-correlation, discharge factor and modified crosscorrelation were analyzed and utilized as inputs to the ENN. The ENN was applied to classify 2 PD datasets. One with PD statistical features and the other a combination of PD statistical features and their correlation coefficients. The results indicate that the ENN appears to show a statistically better performance using the statistical features mixed with their correlation coefficients as compared to the other dataset. This clearly shows that the correlation coefficients of statistical features can provide an improved classification and discrimination of PD patterns.
Original languageEnglish
Title of host publication2nd IEEE International Conference on Dielectrics (ICD) 2018
Place of PublicationPiscataway, N.J.
PublisherIEEE
Number of pages5
DOIs
Publication statusPublished - 1 Nov 2018
Event2nd IEEE International Conference on Dielectrics - Budapest, Hungary
Duration: 1 Jul 20185 Jul 2018
Conference number: 2nd

Conference

Conference2nd IEEE International Conference on Dielectrics
Abbreviated titleICD 2018
CountryHungary
CityBudapest
Period1/07/185/07/18

Keywords

  • partial discharge
  • ensemble neural network
  • correlation coefficients

Fingerprint Dive into the research topics of 'An investigative study on the influence of correlation of PD statistical features on PD pattern recognition'. Together they form a unique fingerprint.

Cite this