Automatic classification and analysis of the characteristic parameters for power quality disturbances

This paper develops an approach to detect and classify power quality disturbance waveforms as well the analysis of the corresponding characteristic parameters using a novel combination of d-q conversion, artificial neural networks, the point to point comparison of ideal voltage with disturbed voltage and wavelet transform. From the results of the d-q conversion through the fictitious three-phase voltages, the classification of voltage sags, swell and interruption is realized. For other disturbances, feature extraction is carried out through the analysis of the results of the d-q conversion, and then artificial neural networks are used for the automatic classification. For the classified disturbances, the corresponding characteristic parameters can be obtained through the analysis of the results of the d-q conversion, the point to point comparison of ideal voltage with disturbed voltage and wavelet transform. Simulation results illustrate the effectiveness of the proposed method.