文档介绍：2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies (DRPT2004) April 2004 Hong Kong
Transmission lines fault detection,
classification and location using an intelligent
Power System Stabiliser
M F Othman, M Mahfouf, and D A Linkens
Abstract- A novel technique, namely optimal feature In this study, a new method is proposed for fault detection
selection in the wavelet domain and supervised neural and classification. A novel technique, called optimal
network-fault classifier is developed. An output signal of the feature selection in the wavelet domain and supervised
speed deviations of each generator of the multi-area multi- work-fault classifier is developed. An output
machines system is taken as the input for the wavelet signal of the speed deviations of each generator of the
analysis. The "oscillation signature" for each of the 4 multi area multi machines system are taken as the input
machines in a 'no fault condition', 'fault' with the PSS and
for the wavelet analysis which are then fed to the
without the PSS is recorded at various fault locations for
fault detection using Multi resolution Analysis (MU) Generalised Regression work (GRNN) and
Wavelet Transforms. The MRA poses the signal into Probabilistic work (PNN) to give the location
different resolutions allowing a detailed