Real-time detection using wavelet transform and neural network of short-circuit faults within a train in DC transit systems

Author

Chang, C.S. ; Kumar, S. ; Liu, B. ; Khambadkone, A.

Author_Institution

Centre for Wavelets Approximation & Inf. Processing, Nat. Univ. of Singapore, Singapore

Volume

148

Issue

3

fYear

2001

fDate

5/1/2001 12:00:00 AM

Firstpage

251

Lastpage

256

Abstract

A method is proposed for the real-time detection of DC-link short-circuit faults in DC transit systems. The discrete wavelet transform is implemented to detect any surges in the DC third-rail current waveform. In the event of a surge the wavelet transform extracts a feature vector from the current waveform and feeds it to a self-organising neural network. The neural network determines whether the feature vector belongs to a normal or a fault current surge

Keywords

discrete wavelet transforms; fault location; power engineering computing; railways; rapid transit systems; self-organising feature maps; starting; surges; DC third-rail current waveform; DC transit systems; DC-link short-circuit faults; current waveform; discrete wavelet transform; fault current surge; feature vector extraction; neural network; normal surge; real-time detection; self-organising neural network; short-circuit faults; starting condition; surges detection; train; wavelet transform;

fLanguage

English

Journal_Title

Electric Power Applications, IEE Proceedings -

Publisher

iet

ISSN

1350-2352

Type

jour

DOI

10.1049/ip-epa:20010350

Filename

927551