Underwater acoustic target ranging method based on feature extraction and neural network

Abstract

The invention discloses an underwater acoustic target ranging method based on feature extraction and a neural network, and the method comprises the steps: 1, collecting underwater acoustic signals transmitted by an underwater acoustic target at different distances, splitting data according to seconds, and enabling the data of one second to serve as a sample; 2, performing framing of each sample; and 3, respectively calculating the zero-crossing rate of the time domain waveform, the second, fifth and eighth coefficients of the MFCC, the frequency spectrum centroid, the frequency spectrum skewness, the frequency spectrum entropy and the frequency spectrum sharpness of each frame of data of each sample. The underwater acoustic target ranging method based on feature extraction and the neural network has the advantages that the received underwater acoustic signal data are directly processed, the real-time performance is high, and the response speed is high.

Description

technical field [0001] The invention relates to the field of underwater acoustic target distance measurement, in particular to a method for underwater acoustic target distance measurement based on feature extraction and neural network. Background technique [0002] At present, countries are paying more and more attention to the consumption, industry and military status of the ocean, and are vigorously conducting related research. Our country is still in a relatively backward stage. Therefore, with the acceleration of my country's military automation construction, the research on underwater acoustic target recognition needs to be promoted urgently. [0003] In the original underwater acoustic target recognition, the existence and distance of the target are mainly determined according to the observer's experience and subjective judgment, and this method has certain disadvantages. Later, acoustic signal theory and modern spectrum theory were used to identify underwater acoust...

AI Technical Summary

Problems solved by technology

[0005] 1. CN110488300A An underwater acoustic positioning system and method: the method requires the target to be positioned to be equipped with a depth sensor for sending depth information, therefore, it is impossible to locate a target without a depth sensor; at the same time, a single array element transducer is used to test The slant distance information is greatly disturbed by the underwater environment, and there is a large measurement error, so the positioning error is large

[0006] 2. CN110208745A An underwater acoustic positioning method based on an adaptive matched filter: the method obtains the specific position of the target to be positioned through the time difference of the two signals, and requires the target to be positioned to install a fixed frequency band sound signal transmission system, and requires an FPGA core The control chip, four hydrophones, four AD processors, four signal amplifiers and one Ethernet transmission module require many types and quantities of equipment and high cost

[0007] 3. CN110542883A is a passive underwater acoustic positioning method for target silence: this method needs to arrange a navigation baseline node array on the water surface, and each node needs to transmit navigation signals synchronously, which cannot be used for real-time positioning of the target to be positioned; at the same time, the method mainly It is used for the positioning of the target to be positioned, and cannot be used for the positioning of the target to be positioned by other devices or systems

Images