Feature selection for identification and classification of power quality disturbances

摘要: Monitoring power quality over extended period of time can result in significant amount data being gathered. This necessitates automatic processing the as captured phenomena need to be sorted before further analysis undertaken. typically involves a process identification and classification various related disturbances. The voltage and/or current waveforms are normally expanded onto some subspaces where there exist patterns for recognizing them. Advanced signal such Fourier transform wavelets generally employed carry out necessary expansion. paper explores features that commonly selected basis identifying A judicious selection is it affects accuracy well efficiency process.