Feature Extraction Method for Ship-Radiated Noise Based on Extreme-point Symmetric Mode Decomposition and Dispersion Entropy

Abstract

A novel feature extraction method for ship-radiated noise based on extreme-point symmetric mode decomposition (ESMD) and dispersion entropy (DE) is proposed in the present study. Firstly, ship-radiated noise signals were decomposed into a set of band-limited intrinsic mode functions (IMFs) by ESMD. Then, the correlation coefficient (CC) between each IMF and the original signal were calculated. Finally, the IMF with highest CC was selected to calculate DE as the feature vector. Comparing DE of the IMF with highest CC by empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD) and ESMD, it is revealed that the proposed method can assist the feature extraction and classification recognition for ship-radiated noise.