Application Of Eemd And High-Order Singular Spectral Entropy To Feature Extraction Of Partial Discharge Signals

Feature extraction of partial discharge (PD) signals is a key step in the pattern recognition and fault diagnosis of power equipment. The theory of singular spectral entropy analysis (SSEA) is introduced in order to study the complexity and irregularity degree of PD signals, but it cannot reflect the inherent nonlinear characteristics. The fourth-order cumulant of PD signals is used instead of the covariance matrix of SSEA, and the ensemble empirical mode decomposition (EEMD) method is applied to realize multiple scales. The proposed multi-scale high-order singular spectral entropy analysis (M-HSSEA) is applied to the simulated PD signals. Noise is effectively suppressed in the extracted entropy eigenvectors, and the robustness of phase space reconstruction parameters can be enhanced as well. Three kinds of typical defect models are designed. The entropy eigenvectors of the PDs detected by the ultra high frequency (UHF) method are extracted. The radial basis function neural network (RBF-NN) classifier is used for pattern recognition. An ideal accuracy can be obtained, which verifies the validity and applicability of the proposed method. (c) 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.