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

Complex radar radiation source identification method based on one-dimensional self-stepping convolutional neural network

A technology of convolutional neural network and recognition method, which is applied in radar radiation source recognition, complex radar radiation source recognition field based on one-dimensional self-paced convolutional neural network, can solve the problem of suppressing radar radiation source classification and recognition accuracy, low recognition rate, It takes a lot of time and other problems to achieve the effect of superior real-time performance, simple network structure and high recognition accuracy

Inactive Publication Date: 2020-12-18
XIDIAN UNIV
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it takes a lot of time to perform time-frequency transformation on the radar emitter signal, and the real-time performance is not strong.
At the same time, the training strategy of randomly feeding samples is not easy to make the network reach the optimal point, thus inhibiting the classification and recognition accuracy of radar radiation sources
[0004] To sum up, in the current increasingly complex and changeable electromagnetic environment, the existing radar radiation source identification methods have poor identification effect and low identification rate, which is not conducive to the judgment of the situation and the adjustment of decision-making

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
  • Complex radar radiation source identification method based on one-dimensional self-stepping convolutional neural network
  • Complex radar radiation source identification method based on one-dimensional self-stepping convolutional neural network
  • Complex radar radiation source identification method based on one-dimensional self-stepping convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021]In today's electromagnetic environment, the radar system is constantly being updated, and the electronic environment is becoming more dense and complex. Effectively identifying radar radiation source signals with high accuracy is a difficult problem in today's electronic warfare, and it is also an important topic. It can not only improve the passive radar system, but also has great research value for the performance improvement of the active radar system. Many experts use two-dimensional convolutional neural networks to identify radar emitter signals. However, the structure of the traditional two-dimensional convolutional neural network is relatively complicated, and the dimensional transformation of the collected one-dimensional radar source signal is required. At the same time, the traditional two-dimensional convolutional neural network has poor recognition effect on radar radiation sources and low recognition accuracy. In view of the above problems, the present invention p...

Embodiment 2

[0033]The complex radar emitter identification method based on the one-dimensional self-stepping convolutional neural network is the same as the seven different modulation types of radar signals described in Example 1, step 1), and the corresponding parameters are set as follows:

[0034]The sampling frequency of these seven different modulation types of radar signals is set to 2GHz, and the number of sampling points is set to 1024;

[0035]The carrier frequency range of conventional pulse signals is 200-220MHz.

[0036]The carrier frequency range of the chirp signal is 200-220MHz, and the bandwidth range is 50-60MHz.

[0037]The nonlinear frequency modulation signal adopts cosine modulation, the carrier frequency range is 200-220MHz, and the modulation signal range is 10-12MHz;

[0038]The carrier frequency range of the two-phase encoded signal is 200-220MHz, the encoding method adopts 13-bit Barker code, the pulse width is 0.5us, and the symbol width is 0.038us.

[0039]The carrier frequency rang...

Embodiment 3

[0044]The complex radar emitter identification method based on the one-dimensional self-stepping convolutional neural network is the same as the construction of the one-dimensional self-stepping convolutional neural network described in Example 1-2, step 3), seefigure 2 , The specific network structure includes the following:

[0045]The first layer is the input layer, the number of nodes is 1024;

[0046]The second layer is a one-dimensional convolution layer with 32 convolution kernels and a convolution kernel size of 33;

[0047]The third layer is a pooling layer with a pooling window of 2, a step size of 2, and a sampling maximum pooling method;

[0048]The fourth layer is the batch normalization layer;

[0049]The fifth layer is a one-dimensional convolution layer with 32 convolution kernels and a convolution kernel size of 33;

[0050]The sixth layer is a pooling layer with a pooling window of 2, a step size of 2, and a maximum sampling pooling method;

[0051]The seventh layer is the batch normal...

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 complex radar radiation source identification method based on a one-dimensional self-stepping convolutional neural network, and solves the problems that in the prior art, dimension transformation processing needs to be carried out on radar signals and the identification rate is low. The implementation scheme comprises the steps of collecting radar radiation source signalsto make a data set; dividing the data set into a training set and a verification set; constructing a one-dimensional self-stepping convolutional neural network; setting a self-stepping sample trainingstrategy and training the network by using the training set; and inputting the data of the test set into the trained one-dimensional self-stepping convolutional neural network, and outputting the recognition rate of the overall test signal. The one-dimensional self-stepping convolutional neural network constructed by the method is simple in structure and small in parameter quantity, can directlyextract the time domain signal characteristics of the one-dimensional radar radiation source, does not need dimension transformation, and is good in real-time performance. Meanwhile, a self-stepping sample training strategy is adopted, so that the network is close to the optimal point as much as possible in the training process, and the recognition rate is increased. The method can be used for radar radiation source identification in a complex electromagnetic environment.

Description

Technical field[0001]The invention belongs to the technical field of signal processing, and particularly relates to a radar radiation source identification, in particular to a complex radar radiation source identification method based on a one-dimensional self-stepping convolutional neural network, which can be used in electronic intelligence reconnaissance, electronic support and threat warning systems in.Background technique[0002]Electronic countermeasures play an important role in electronic intelligence reconnaissance, electronic support and threat warning systems. Radar source signal identification is an important part of electronic countermeasures. With the development and advancement of science and technology, the radar system is constantly updated, and the electronic environment is becoming more dense and complex, which increases the difficulty of extracting characteristic parameters from the received radar signal. Furthermore, the received radar radiation source signal ofte...

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): G01S7/36G01S7/41G06N3/04G06N3/08
CPCG01S7/36G01S7/417G06N3/08G06N3/045
Inventor 武斌袁士博李鹏王钊张葵荆泽寰殷雪凤
Owner XIDIAN 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