Classification of partial discharge EMI conditions using permutation entropy-based features

Imene Mitiche, Gordon Morison, Alan Nesbitt, Philip Boreham, Brian G. Stewart

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

7 Citations (Scopus)
18 Downloads (Pure)


In this paper we investigate the application of feature extraction and machine learning techniques to fault identification in power systems. Specifically we implement the novel application of Permutation Entropy-based measures known as Weighted Permutation and Dispersion Entropy to field Electro- Magnetic Interference (EMI) signals for classification of discharge sources, also called conditions, such as partial discharge, arcing and corona which arise from various assets of different power sites. This work introduces two main contributions: the application of entropy measures in condition monitoring and the classification of real field EMI captured signals. The two simple and low dimension features are fed to a Multi-Class Support Vector Machine for the classification of different discharge sources contained in the EMI signals. Classification was performed to distinguish between the conditions observed within each site and between all sites. Results demonstrate that the proposed approach separated and identified the discharge sources successfully.
Original languageEnglish
Title of host publication25th European Signal Processing Conference (EUSIPCO)
Place of PublicationPiscataway, NJ.
Number of pages5
ISBN (Electronic)9780992862671
Publication statusPublished - 26 Oct 2017


  • partial discharge
  • classification
  • Electro Magnetic Interference
  • EMI
  • power systems
  • high voltage power plants


Dive into the research topics of 'Classification of partial discharge EMI conditions using permutation entropy-based features'. Together they form a unique fingerprint.

Cite this