Feature analysis and automatic classification of short-circuit faults resulting from external causes

Authors


Correspondence to: Victor Barrera Núñez, IIiA Research institute, University of Girona (UdG), EPS, Campus Montilivi, Girona, zip: 17071, Spain.

E-mail: victor.barrera@udg.edu

SUMMARY

This paper aims to determine unique features in voltage and current waveforms of a given disturbance event so as to automatically identify its root cause. In particular, the paper focuses on short-circuit faults caused by external factors such as animal and tree contacts, lightning-induced events, and cable failures. The proposed methodology consists of analyzing sets of known events caused by similar external agents to identify unique features characterizing the set and at the same time discriminate the remaining event subset. The proposed methodology has been implemented and tested using real-world fault events with a classification rate of 93.4%. This result demonstrates a good performance in identifying the cause of the events. In addition, the methodology rejects those events that do not follow any cause. Copyright © 2012 John Wiley & Sons, Ltd.

Ancillary