Classification and identification of over-voltage based on HHT and SVM

Abstract

This paper introduces the Hilbert-Huang transform method which is composed of Empirical Mode Decomposition (EMD) and Hilbert Transform. Seven kinds of common power system over-voltages are analyzed by HHT, 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. A hierarchical recognition system is built based on HHT and SVM, and the system is tested by field over-voltage signals. The results show that this system is effective to classify and recognize the over-voltage signal with a high recognition rate.