Abstract
In the field of underwater acoustic signal processing, the ship radiated noise contains a large amount of ship information, which is of great significance to the ship identification. The traditional method relies too much on the operator and prior knowledge, which seriously reduces the efficiency and accuracy of the ship radiated noise identification. This paper presented a novel ship radiated noise feature extraction method based on compression sensing and center frequency. Firstly, to compression sensing of the ship radiated noise, enhance its line spectrum energy. Then, the ship radiated noise is decomposed by empirical mode decomposition to obtain multiple intrinsic mode function, calculate the mutual information entropy of adjacent intrinsic mode function to determine the key parameter K of the variational mode decomposition. Finally, perform variational model of ship radiated noise based on K, extract the center frequency of maximum energy intrinsic mode function as the ship radiated noise recognition feature. Experimental results show that the proposed feature extraction method can classify ship radiated noise quickly and effectively, and reduce the dependence on operators and prior knowledge.
Highlights
Ocean is the main battlefield of the future science and technology war[1]
The research on feature extraction of underwater target radiated Noise mainly focuses on four aspects: power spectrum estimation and Low Frequency Analysis recording (LOFAR) Analysis, Detection of Envelope Modulation on Noise (DEMON) spectrum Analysis, multi-scale feature extraction and high-order spectrum Analysis
Bai et al[24] used the improved maximum common divisor algorithm and remainder threshold algorithm to extract the axis frequency and blade frequency of the DEMON spectrum, which solves the problem that the traditional maximum common divisor algorithm has a large error in extracting axis frequency and blade frequency, and verifies the effectiveness of extracting ship radiation noise features from the DEMON spectrum
Summary
Ocean is the main battlefield of the future science and technology war[1]. The radiated noise of underwater targets such as ships contains abundant ship information[2]. The research on feature extraction of underwater target radiated Noise mainly focuses on four aspects: power spectrum estimation and Low Frequency Analysis recording (LOFAR) Analysis, Detection of Envelope Modulation on Noise (DEMON) spectrum Analysis, multi-scale feature extraction and high-order spectrum Analysis. Through the time-frequency analysis of the radiation noise of the underwater target, the time-domain signal is converted to the frequency domain, and the distribution of each frequency quantity is compared, so as to identify the type and speed of the underwater target He et al[10] combined power Spectrum density Estimation and Higher Order Spectrum to extract the distinguishable features of underwater target radiation Noise. DEMON spectrum analysis method is used to classify physical characteristic signals such as axis frequency and blade frequency in the discrete line spectrum of modulated ship radiation noise, which requires high prior knowledge of operators and limits its popularization and use. The experimental results show that the recognition rate of this method is 94%, which can be used in real time processing
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
