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

Multicomponent Radar Signal Modulation Recognition Method Based on Blind Compressive Kernel Dictionary Learning

A radar signal and dictionary learning technology, applied in the field of radiation source signal identification, can solve the problems of weak adaptability of identification methods, difficulty in ensuring identification accuracy, and difficulty in forming a unified structure, so as to reduce training complexity and improve identification accuracy. , the effect of good time-frequency aggregation

Active Publication Date: 2022-05-20
HARBIN ENG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, due to the complex and diverse signal mixing methods, it is difficult to form a unified structure in the recognition process, which makes it difficult to guarantee the recognition accuracy and weak adaptability of the recognition method

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
  • Multicomponent Radar Signal Modulation Recognition Method Based on Blind Compressive Kernel Dictionary Learning
  • Multicomponent Radar Signal Modulation Recognition Method Based on Blind Compressive Kernel Dictionary Learning
  • Multicomponent Radar Signal Modulation Recognition Method Based on Blind Compressive Kernel Dictionary Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following examples describe the present invention in more detail.

[0029] The specific steps of the multi-component radar signal modulation recognition method based on blind compression kernel dictionary learning of the present invention are as follows:

[0030] Step 1: According to the 14 types of radar conventional signal parameters, generate conventional pulse signal (CW), linear frequency modulation signal (LFM), nonlinear frequency modulation signal (NLFM), frequency modulation coded signal (Costas), biphase coded signal (BPSK), Radar single-signal training set composed of multi-phase encoded signals (Frank, P1, P2, P3, P4) and multi-time code signals (T1, T2, T3, T4), and random selection of radar single signals into multi-component radar signal training Set, set the number of signal points to 1024.

[0031] Step 2: From the radar single-signal training set and the multi-component signal training set, extract the radar single-signal and multi-component signa...

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 provides a multi-component radar signal modulation recognition method based on blind compression kernel dictionary learning. Using Choi-Williams time-frequency distribution (CWD) to obtain the time-frequency matrix of multi-component radar signals, using preprocessing technology to reduce the dimension of the time-frequency matrix, and introducing the idea of ​​blind compression, using Bernoulli random matrix to further compress the time-frequency matrix losslessly , the data set is projected from the low-dimensional space to the high-dimensional space through the kernel dictionary learning algorithm, and the multi-signal is represented without separating the multi-component signal. Finally, the obtained sparse coefficient vector is sent to the support vector machine for modulation Accurate identification. The invention solves the problems of high complexity, weak adaptability, poor reliability and slow convergence speed in the multi-component radar signal modulation identification process.

Description

technical field [0001] The invention relates to a radiation source signal identification method, in particular to a multi-component radar signal modulation identification method. Background technique [0002] Radar signal modulation recognition is an important means to obtain radar information. As the electromagnetic signals become more and more dense, there are multiple signals arriving at the same time in the acquired signals, which brings difficulties to the identification of the classifier. There are mainly two kinds of existing radar multi-component signal modulation recognition methods: multi-signal modulation recognition based on signal separation and multi-signal modulation recognition based on direct feature extraction. [0003] The multi-component signal modulation recognition method based on signal separation adopts time filtering or spatial filtering method to separate multiple signals that are aliased in the time domain from the mixed waveform one by one, and t...

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 Patents(China)
IPC IPC(8): G01S7/292G01S7/295G06K9/00G06K9/62
CPCG01S7/2923G01S7/295G06F2218/12G06F18/21345G06F18/2411
Inventor 郜丽鹏张晓丽高敬鹏王欢朱嘉颖沙作金
Owner HARBIN ENG UNIV
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