Abstract
Sea environment complexity and underwater acoustic channels make it hard to extract features of ship-radiated noise signals. This paper presents a novel feature extraction method using the advantages of variational mode decomposition (VMD), fluctuation-based dispersion entropy (FDE) and self-organizing feature map (SOM). Firstly, VMD decomposition of the original signal is used to get a group of bandwidth-limited intrinsic mode functions (IMFs). Then, the difference between the FDE of each IMF and the original signal is calculated, respectively; the IMF with the smallest difference (SIMF) is selected to calculate the FDE as the feature vector. Finally, the characteristic vectors are sent to the SOM classifier to categorize the original signal. The proposed method is applied to feature extraction of real ship-radiated noise signals. The results show that this method is more precise for ship-radiated noise signals feature extraction.
Highlights
Feature extraction is a key link of target classification
The results show that this method is more precise for ship-radiated noise signals feature extraction
The four types of ship-radiated noises are decomposed by using variational mode decomposition (VMD), and the intrinsic mode functions (IMFs) with the smallest fluctuation-based dispersion entropy (FDE) difference is obtained
Summary
Feature extraction is a key link of target classification. Sea environment complexity and underwater acoustic channels make it hard to extract features of ship-radiated noise signals that reflects the essential characteristics of the target and meet the requirements of underwater long-distance detection [1]. This method is no longer dependent on the frequency domain and implements fast algorithms; at the same time, it has a good ability to suppress noise components in non-stationary signals It is still affected by the wavelet basis function and decomposition level [8]. Empirical Mode Decomposition (EMD) is a new method to analyze non-stationary and non-linear signals in the signal processing field It is a self-adaptive complete orthogonal decomposition according to the characteristics of the signal itself and can extract the eigenmode component of the dynamic signal [9,10]. Based on the above analysis, this paper uses the advantages of VMD, FDE and SOM to propose a new method to extract ship-radiated noise characteristics.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
