Real-time detection using wavelet transform and neural network of short-circuit faults within a trai - Electric Power Applications, IEE Proceedings-.pdf

文档介绍：Real-time detection using wavelet transform and neural
network of short-circuit faults within a train in DC transit
systems
, , and
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 anising work. The work determines
whether the feature vector belongs to a normal or a fault current surge.
Principal symbols could endanger the lives of train passengers as well as cause
extensive damage to traction equipment.
equivalent impedance of third rail and return tracks
chopper-motor-
DC-link capacitor I rectifier 1 track I filter I mechanical load I
level of position in discrete wavelet transform
maximum level of position in discrete wavelet I
transform
I
mother wavelet function I
I
dilation parameter I I
translation parameter Fig. 1 Short-circuitfmlt in DC trmsit systm
discrete time parameter of wavelet basis function Presently the current relays used in the detection of
length of DC sample short-circuit faults in DC transit systems are based on
input pattern vector to work current magnitude and gradient