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

A neural network and feature extraction technology, applied in neural learning methods, biological neural network models, measuring devices, etc., can solve problems such as inability to achieve positioning without depth sensors, inability to use positioning targets for real-time positioning, large measurement errors, etc., to achieve cost Low, low average relative error, and the effect of avoiding manual intervention

Active Publication Date: 2020-09-04
SUZHOU UNIV
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Underwater acoustic target ranging method based on feature extraction and neural network
  • Underwater acoustic target ranging method based on feature extraction and neural network
  • Underwater acoustic target ranging method based on feature extraction and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0045] 1. Collect the underwater acoustic signals sent by the underwater acoustic target at different distances, and split the data by second, and the data of one second is taken as a sample;

[0046] 2. Divide each sample into frames, set the frame length to 20ms, and set the frame shift to 10ms;

[0047] 3. Calculate the zero-crossing rate of the time-domain waveform, the 2nd, 5th, and 8th coefficients of MFCC, spectral centroid, spectral skewness, spectral entropy, and spectral sharpness for each frame of data of each sample;

[0048] The zero-crossing rate (ZCR) is defined as:

[0049]

[0050] Among them, N is the number of sampling points per frame, and x(q) is the ampli...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01S11/14G06N3/08
CPCG01S11/14G06N3/08G06N3/084
Inventor 肖仲喆石拓江均均黄敏吴迪
Owner SUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products