The Fourier transform can be used for analysis of nonstationary signals, bu
t the Fourier spectrum does not provide any time-domain information about t
he signal. When the time localization of the spectral components is needed,
a wavelet transform giving the time-frequency representation of the signal
must be used. In this paper, using wavelet analysis and neural systems as
a new tool for the analysis of power system disturbances, disturbances are
automatically detected, compacted, and classified. An example showing the p
otential of these techniques for diagnosis of actual power system disturban
ces is presented.