Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Underwater acoustic target recognition method based on signal processing and deep-shallow network multi-model fusion

A technology of signal processing and target recognition, which is applied to pattern recognition in signals, biological neural network models, character and pattern recognition, etc., can solve problems such as shortage, achieve stable high recognition ability, stable high environmental tolerance, and improve efficiency Effect

Active Publication Date: 2021-02-12
NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
View PDF10 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still a lack of such a solution in the prior art

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 recognition method based on signal processing and deep-shallow network multi-model fusion
  • Underwater acoustic target recognition method based on signal processing and deep-shallow network multi-model fusion
  • Underwater acoustic target recognition method based on signal processing and deep-shallow network multi-model fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0045] An underwater acoustic target recognition method based on the fusion of signal processing and deep-shallow network multi-model. This method first preprocesses the target signal data collected by the passive reconnaissance array by signal processing, filters out interference and extracts target features, and then uses volume A multi-model recognition architecture is built using a product neural network (CNN) and a residual network (ResNet), and finally a voting decision-making mechanism is introduced to realize the classification and recognition of maneuvering targets in water. Specifically include the following steps:

[0046] (1) Filter and denoise the radiated noise signal of the underwater acoustic target received by the array to obtain "clean" and enhanced target time-domain signal data;

[0047] (2) Do domain transformat...

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 recognition method based on signal processing and deep-shallow network multi-model fusion, and belongs to the technical field of underwater acoustic target passive reconnaissance. According to the method, target signal data acquired by a passive reconnaissance array are preprocessed by using a signal processing method, interference is filteredout, target features are extracted, then a multi-model recognition architecture is constructed by using a convolutional neural network and a residual network, and finally a voting decision mechanism is introduced to realize classification and recognition of maneuvering targets in water. Sonar signal processing is used as preprocessing to solve the problem that clean samples are difficult to obtainunder complex sea conditions; multi-dimensional features are adopted as training samples to improve adaptive capacity and recognition accuracy under different sea conditions and working conditions; the recognition accuracy and robustness of the method are improved based on fusion recognition of a multi-neural-network model.

Description

technical field [0001] The invention belongs to the technical field of passive reconnaissance of underwater acoustic targets, in particular to an underwater acoustic target recognition method in which signal processing and deep-shallow network multi-model fusion are used, which can be used to analyze target radiation noise signals collected by detection arrays. Background technique [0002] Passive classification and recognition of underwater acoustic targets is an information processing technology that analyzes and processes target radiation noise signals received by sonar equipment, extracts target features, and identifies target types. Commonly used target classification and recognition methods mainly include statistical classification, model matching, and expert systems. There are application limitations. In addition, if the attribute of an unknown target is judged based on information such as the beat, timbre, fluctuation, and spectrum of the noise signal, it will inev...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/04G06F2218/08G06F2218/12
Inventor 罗恒光张博轩王大宇宋高宇曾昕
Owner NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com