A comparative study of four multi-scale entropies combined with grey relational degree in classification of ship-radiated noise

Abstract

In order to improve the classification performance of ship-radiated noise effectively, a comparative study of four multi-scale entropies is carried out by combining with grey relational degree (GRD) and a novel classification method for ship-radiated noise is proposed based on multi-scale reverse dispersion entropy (MRDE) and GRD, named MRDE-GRD. In this paper, MRDE is applied to the complexity feature extraction of ship-radiated noise under different scales, and GRD is used to identify different kinds of ship-radiated noise by calculating the GRD of the ship to be identified and reference ships. Experimental results show that the proposed MRDE-GRD classification method can effectively extract the complexity features of ship-radiated noise, and has better classification performance than the other three classification methods based on multi-scale permutation entropy (MPE), multi-scale weighted permutation entropy (MWPE) and multi-scale dispersion entropy (MDE) combined with GRD, named MPE-GRD, MWPE-GRD, and MDE-GRD. It is proved that the proposed classification method for ship-radiated noise is effective and achieves a recognition rate of 97.75%.