Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Satellite Target Recognition Method Based on Broadband Radar Data and Gru Neural Network

A broadband radar and neural network technology, applied in the field of satellite target recognition, can solve problems such as weak generalization ability, large uncertainty, and difficulty in effectively describing radar HRRP characteristics, so as to improve accuracy, improve recognition rate, reduce Search scope and calculated effects

Active Publication Date: 2021-01-29
PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The design and selection of the above features takes a lot of time and energy, and there is a lot of uncertainty at the same time, and the generalization ability for different radars and different target types is weak; the third is to use machine learning algorithms to extract the dimensionality reduction features of HRRP, such as the main Component analysis (Principal Component Analysis, PCA), dictionary learning and manifold learning, etc.
But they are all shallow networks, it is difficult to effectively describe the HRRP characteristics of the radar, and obtain the deep feature information of the data

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
  • A Satellite Target Recognition Method Based on Broadband Radar Data and Gru Neural Network
  • A Satellite Target Recognition Method Based on Broadband Radar Data and Gru Neural Network
  • A Satellite Target Recognition Method Based on Broadband Radar Data and Gru Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The embodiment of the present invention provides ten kinds of satellite target recognition based on broadband radar data and GRU neural network. Each satellite target has 70,000 pieces of HRRP data, and the dimension of each piece of HRRP data is 300. Since the radar observation angle does not change much in a relatively short period of time, for the sake of convenience, it is assumed that the 700 consecutive HRRP data have the same radar observation angle. figure 1 The flowchart of satellite target recognition method based on broadband radar data and GRU neural network proposed by the present invention is given.

[0040] Such as figure 1 As shown, Embodiment 1 of the present invention provides a satellite target recognition method based on broadband radar data and GRU neural network, including:

[0041] Step 1. Preprocessing the broadband radar HRRP data, the preprocessing includes envelope alignment and amplitude normalization. The preprocessing steps include: perfo...

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 satellite target recognition method based on broadband radar data and GRU neural network, the method mainly includes two parts of data division and deep learning model, by introducing orbital height and radar observation angle information into satellite target recognition, realizing The division of broadband radar HRRP training data corresponds to the matching of test data; GRU neural network is used to extract the effective features of HRRP data, and the divided HRRP training data is used as input to determine the weight space of GRU neural network through network training in order to extract HRRP test The deep essential features of the data are input into the classifier to realize satellite target recognition. The present invention can make full use of the existing broadband radar data, and use the deep learning model of GRU neural network to extract the deep-level features of the radar HRRP data, which is beneficial to extract the effective features of the training data and reduce the search range and calculation amount of the test data , improving the accuracy of satellite target recognition.

Description

technical field [0001] The invention belongs to the technical field of radar automatic target recognition, in particular to a satellite target recognition method based on broadband radar data and a GRU neural network. Background technique [0002] Space is an important part of modern life style, national security and modern warfare. All countries in the world attach great importance to the development of their space capabilities. Therefore, aerospace technology has developed rapidly, and more and more advanced satellites have been launched into space, making space increasingly crowded, more competitive and confrontational. How to effectively perceive the space situation and improve space monitoring capabilities has become a major problem faced by major aerospace countries. Among them, satellite target recognition is an important function of the space monitoring information system. As an effective and important means to perceive the space situation, broadband radar has the c...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06V2201/07G06N3/045G06F18/23G06F18/2414
Inventor 卢旺张雅声徐灿方宇强林财永霍俞蓉冯飞杨虹胡盟霄
Owner PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG 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
Eureka Blog
Learn More
PatSnap group products