Application of Hilbert-Huang Transform to Power System Over-voltage Recognition

We introduced the Hilbert-Huang transform method which was composed of empirical mode decomposition (EMD) and Hilbert Transform to over-voltage signal recognition and classification.Seven kinds of common electric power system over-voltage signals were analyzed by the HHT method.The results show that the instantaneous amplitude spectrum,Hilbert marginal spectrum,Hilbert time-frequency spectrum can be used as characteristic parameters for different types of over-voltage classification and identification.Over-voltage signal hierarchical recognition system was built based on the HHT and RBF neural network,then the system was tested by field over-voltage signals.The results show that the system is effective to classify and recognize the over-voltage signal at a high recognition rate.