Research on Feature Extraction Method for Ship Radiated Noise Based on DBO-VMD

In order to effectively extract the frequency characteristics of underwater acoustic signals in complex marine background, a variational mode decomposition algorithm (VMD) based on dung beetle optimization algorithm (DBO) is proposed to extract the radiation noise features of ships. Aiming at the problem that the initial parameters of the VMD algorithm are difficult to set, the dung beetle optimization algorithm is used to select the local minimum sample entropy as the fitness function of the algorithm, and the best combination of the initialized parameter mode number and the penalty factor in the VMD algorithm is searched, so that the performance of the VMD algorithm is optimal, and the corresponding IMF components are obtained by decomposing the ship radiation noise signal. Experiments show that the center frequency of the IMF component with the highest degree of correlation with the original signal are good separability for ships as characteristic parameters.