A New Method for Power Quality Mixed Disturbance Classification Based on Time-frequency Domain Multiple Features

A new method for power quality mixed disturbance classification,based on time-frequency domain multiple features,was presented in the paper.Firstly,the disturbance signals were processed with ensemble empirical mode decomposition and modified incomplete S-transformation,and nine time-frequency domain characteristics were extracted.Then,the characteristics were input into the sub-block of the automatic classification system for the disturbance identification.In this method,interferences between the single disturbances were fully considered and effectively suppressed through the complementary amount of time and frequency domain features.The simulation results show that the method can effectively recognize the power quality mixed disturbances with the noise including voltage sag,voltage swell,voltage interruption,impulsive transient,oscillation transient,harmonics,flicker and their mixed ones.