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

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.

[1]  Vladimir Terzija,et al.  Time domain solution of fault distance estimation and arcing faults detection on overhead lines , 1999 .

[2]  Surya Santoso,et al.  Waveform characteristics of underground cable failures , 2010, IEEE PES General Meeting.

[3]  Irene Yu-Hua Gu,et al.  Feature characterization of power quality events according to their underlying causes , 2010, Proceedings of 14th International Conference on Harmonics and Quality of Power - ICHQP 2010.

[4]  Surya Santoso,et al.  Feature analysis and classification methodology for overhead distribution fault events , 2010, IEEE PES General Meeting.

[5]  E. Styvaktakis,et al.  Expert System for Classification and Analysis of Power System Events , 2002, IEEE Power Engineering Review.

[6]  Mo-Yuen Chow,et al.  Power Distribution Fault Cause Identification With Imbalanced Data Using the Data Mining-Based Fuzzy Classification $E$-Algorithm , 2007, IEEE Transactions on Power Systems.

[7]  Joaquim Melendez,et al.  SVM-based classification methodology for overhead distribution fault events , 2010, Proceedings of 14th International Conference on Harmonics and Quality of Power - ICHQP 2010.

[8]  Mo-Yuen Chow,et al.  A classification approach for power distribution systems fault cause identification , 2006, IEEE Transactions on Power Systems.

[9]  Irene Y. H. Gu,et al.  Classification of Underlying Causes of Power Quality Disturbances: Deterministic versus Statistical Methods , 2007, EURASIP J. Adv. Signal Process..

[10]  Emmanouil Styvaktakis.  Automating Power Quality Analysis , 2002 .

[11]  Peter Clark,et al.  The CN2 Induction Algorithm , 1989, Machine Learning.

[12]  Lexin Li,et al.  Evaluation of distribution fault diagnosis algorithms using ROC curves , 2010, IEEE PES General Meeting.

[13]  Chen-Fu Chien,et al.  Rough set theory for data mining for fault diagnosis on distribution feeder , 2004 .

[14]  Lexin Li,et al.  Statistical Feature Selection From Massive Data in Distribution Fault Diagnosis , 2010, IEEE Transactions on Power Systems.

[15]  Duehee Lee,et al.  Waveform characterization of animal contact, tree contact, and lightning induced faults , 2010, IEEE PES General Meeting.

[16]  Seon-Ju Ahn,et al.  Determination of the relative location of voltage sag source according to event cause , 2004, IEEE Power Engineering Society General Meeting, 2004..