Machine learning techniques for diagnosing and locating faults through the automated monitoring of power electronic components in shipboard power systems

Author

Mair, A.J. ; Davidson, E.M. ; McArthur, S.D.J. ; Srivastava, S.K. ; Schoder, K. ; Cartes, D.A.

Author_Institution

Inst. for Energy & Environ., Univ. of Strathclyde, Glasgow

fYear

2009

fDate

20-22 April 2009

Firstpage

469

Lastpage

476

Abstract

The management and control of shipboard medium voltage AC (MVAC) and medium voltage DC (MVDC) power system architectures under fault conditions present a number of challenges. The use and resulting interaction of multiple power electronic components in mesh-like power distribution architectures possibly result in the effects of faults being detectable throughout the system, for example, line-to-hull faults on DC systems with high resistive grounding.

Keywords

belief networks; decision trees; fault location; learning (artificial intelligence); power electronics; power engineering computing; ships; support vector machines; Bayesian networks; automated monitoring; decision trees; fault diagnosis; fault location; machine learning; medium voltage DC power system architectures; nearest neighbour classifiers; power electronic components; radial basis function networks; shipboard medium voltage AC; shipboard power systems; support vector machines; Computerized monitoring; Condition monitoring; Control systems; Energy management; Machine learning; Medium voltage; Power electronics; Power system faults; Power system management; Voltage control;

fLanguage

English

Publisher

ieee

Conference_Titel

Electric Ship Technologies Symposium, 2009. ESTS 2009. IEEE

Conference_Location

Baltimore, MD

Print_ISBN

978-1-4244-3438-1

Electronic_ISBN

978-1-4244-3439-8

Type

conf

DOI

10.1109/ESTS.2009.4906553

Filename

4906553