Radar interference signal feature-level fusion identification method based on deep convolutional neural network

A convolutional neural network and radar jamming technology, which is applied in the field of radar jamming signal feature-level fusion recognition, can solve problems such as features that are easily affected by noise and redundancy, and achieve the effect of reducing impact and facilitating design.

Active Publication Date: 2020-02-21
HARBIN INST OF TECH
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the characteristic parameters of the current radar jamming signal rely on manual extraction, are easily affected by noise and have feature redundancy, the present invention provides a radar jamming signal feature-level fusion recognition method based on a deep convolutional neural network

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
  • Radar interference signal feature-level fusion identification method based on deep convolutional neural network
  • Radar interference signal feature-level fusion identification method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0042] Specific implementation mode 1. Combination figure 1 and figure 2 As shown, the present invention provides a radar jamming signal feature level fusion recognition method based on a deep convolutional neural network, including establishing a radar jamming time domain data set, and using two types of radar jamming time domain data in the radar jamming time domain data set The feature vectors are extracted in different forms, and then the two extracted feature vectors are fused in series; the fused feature vectors are used to train the support vector machine, and the trained radar jamming signal feature-level fusion recognition model is obtained;

[0043] The two kinds of feature vectors extracted include: feature vectors extracted by using a one-dimensional convolutional neural network and expert feature vectors extracted manually;

[0044] Or use the feature vector extracted by a one-dimensional convolutional neural network and the time-frequency domain feature vector ...

specific Embodiment 1

[0050] to combine figure 1 As shown, for the eigenvector extracted by one-dimensional convolutional neural network and the expert eigenvector extracted manually, the process of obtaining the feature-level fusion recognition model of radar jamming signal includes:

[0051] Artificial feature parameter extraction is performed on the radar interference time domain data, and the obtained expert feature vector includes time domain moment skewness, time domain moment kurtosis, time domain signal envelope fluctuation, time domain interference signal mean and time domain interference signal variance ;

[0052] At the same time, the radar interference time domain data is divided into training set, verification set and test set;

[0053] The data in the training set is extracted using a one-dimensional convolutional neural network to extract the training sample feature vector, and the training sample feature vector is subjected to PCA processing, and then the PCA-processed feature vect...

specific Embodiment 2

[0072] combine figure 2 As shown, for the feature vectors extracted by using one-dimensional convolutional neural network and the time-frequency domain feature vectors extracted by using deep convolutional neural network, the process of obtaining the feature-level fusion recognition model of radar jamming signals includes:

[0073] Divide radar jamming time domain data into time domain training set, time domain validation set and time domain test set;

[0074] Use one-dimensional convolutional neural network to extract time-domain training sample feature vectors for the data in the time-domain training set;

[0075] At the same time, time-frequency transformation is performed on the radar interference time-domain data to obtain radar interference time-frequency domain data, and the radar interference time-frequency domain data is divided into time-frequency domain training set, time-frequency domain verification set and time-frequency domain test set;

[0076] The time-frequ...

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 a radar interference signal feature-level fusion identification method based on a deep convolutional neural network, and belongs to the field of radar interference signal identification. The method aims to solve the problems that feature parameters of radar interference signals at present depend on manual extraction, are easily affected by noise and have feature redundancy.The method comprises the following steps: establishing a radar interference time domain data set, extracting feature vectors from radar interference time domain data in the radar interference time domain data set in two different forms, and carrying out series fusion on the two extracted feature vectors; training a support vector machine by adopting the fused feature vectors to obtain a trained radar interference signal feature-level fusion recognition model; and inputting the collected test sample into the identification model to obtain a radar interference signal identification result. According to the method, the CNN is utilized to extract the deep features of the radar interference signals, and different radar interference signal data fusion models are designed at the feature level, so that signal identification is not affected by noise, and meanwhile, the feature redundancy phenomenon is eliminated.

Description

technical field [0001] The invention relates to a radar interference signal feature-level fusion recognition method based on a deep convolutional neural network, and belongs to the field of radar interference signal recognition. Background technique [0002] With the increasing complexity of the electromagnetic environment and the increasing number of interference patterns, in order to ensure that the radar can still play an effective role in tracking and detection in extremely harsh electromagnetic environments, it is necessary to greatly improve the anti-interference performance. Anti-jamming capability of radar equipment. The key and basis of radar anti-jamming technology is to be able to efficiently classify and identify radar jamming signals. Therefore, it is an urgent problem to be solved whether to design a jamming signal recognition model with high recognition accuracy and strong robustness. [0003] One of the core steps in the identification process of radar jamm...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/254G06F18/253
Inventor 邵广庆陈雨时于雷位寅生李迎春
Owner HARBIN INST OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap