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

Deep reinforcement learning anti-interference method for frequency agile radar

A technology of frequency agility and reinforcement learning, which is applied in design optimization/simulation, climate sustainability, instruments, etc., can solve problems such as motion overestimation of DQN algorithm, and achieve the goal of helping learning algorithm design, speeding up training, optimizing The effect of convergence performance

Active Publication Date: 2022-05-17
SICHUAN UNIV
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problem of overestimation of the motion of the DQN algorithm itself when the DQN algorithm is used in the prior art in the face of a frequency-agile radar in a highly dynamic electromagnetic interference environment

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
  • Deep reinforcement learning anti-interference method for frequency agile radar
  • Deep reinforcement learning anti-interference method for frequency agile radar
  • Deep reinforcement learning anti-interference method for frequency agile radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] figure 1 It shows the overall structure diagram of the anti-jamming model proposed in the exemplary embodiment of the present invention, such as figure 1 Shown; an anti-jamming system for frequency-agile radar, including: intelligent reinforcement learning algorithm model, radar, jammer and detection target;

[0057] The intelligent reinforcement learning algorithm is used to output a strategy based on environmental information and make the radar transmit pulse carrier frequency continuously randomly jump to suppress the jamming signal of the jammer;

[0058] The jammer is used to intercept the carrier frequency information of the target detection pulse signal and then use the jamming strategy to exert jamming;

[0059] The radar is a frequency-agile radar, which is used to transmit a detection pulse signal to the detection target according to the strategy output by the intelligent reinforcement learning algorithm;

[0060] The detection target is used to reflect a ta...

Embodiment approach

[0071] As a preferred embodiment of the present invention, the interference strategy J π For: variable center blocking jamming or hybrid jamming with memory

[0072] The variable center blocking jamming is: the jammer according to the preset radar pulse signal center frequency f n and spectral width Δfr , to determine the center frequency f of the interfering signal j0 and spectral width Δf j , for the frequency band range [f j0 -Δf j / 2,f j0 +Δf j / 2] to block the radar pulse signal;

[0073] The hybrid jamming with memory is: a complete CPI of the jammer's reconnaissance radar transmission signal, the frequency of N pulses in a CPI is memorized; the optimal coverage parameter δ of the blocking jamming is given, and Q deceptive jamming signals are superimposed Afterwards, interference is performed on all pulses in the next CPI; in addition, the same spoofing interference part is generated in the next pulse according to the frequency of the previous pulse.

[0074] Fur...

Embodiment 2

[0106] Specifically, on the basis of Embodiment 1, this embodiment adopts the Python language, based on the Pytorch simulation tool, and the specific simulation parameters are as follows:

[0107]

[0108] It should be noted that the parameter setting does not affect the generality of this simulation, that is, the parameter setting can be modified within a reasonable range. In this embodiment, it is set that if the jammer adopts blocking interference, its interference power is distributed in a bandwidth of 2B and compared to On the B-wide frequency band, if the jammer adopts suppressive interference, its interference power is distributed in the frequency band with a bandwidth of 200MHz, covering all possible frequencies within a CPI on the frequency-agile radar.

[0109] The jamming strategy preferably used in this embodiment is as follows: variable center blocking jamming: jammer according to preset radar pulse signal center frequency f n and spectral width Δf r , to dete...

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 relates to the technical field of radar anti-interference, in particular to a deep reinforcement learning anti-interference method for a frequency agile radar. The method can be applied to robust and convergent frequency strategy learning in a large-scale decision space and a complex interference environment. An intelligent frequency strategy learning method based on an active confrontation idea and a deep reinforcement learning technology endows the frequency agility radar with the capability of actively confronting main lobe interference; according to the method, a confrontation decision process is established on a Markov decision model, and a deep reinforcement learning design intelligent confrontation strategy for processing a large-scale discrete space is introduced, so that the adaptive capacity of a radar in a complex high-dynamic environment can be improved; the method provided by the invention can adapt to a complex interference model, and the interference environment is depicted as a suppressing and deception mixed interference model with high flexibility, so that the method has higher strategic performance and authenticity.

Description

technical field [0001] The invention relates to the technical field of radar anti-jamming, in particular to a deep reinforcement learning anti-jamming method for frequency-agile radar. Background technique [0002] With the update and development of the modern electronic combat environment, new system interference patterns and interference strategies are constantly being formed in the field of electronic countermeasures, which brings new challenges to radar target recognition. Traditional radar countermeasure technology combines environmental perception and intelligent anti-jamming capabilities research has gradually become mainstream. Among them, the frequency-agile radar utilizes the flexible and changeable characteristics of the frequency domain, which can avoid being captured by jammers to a certain extent, and has superior performance in the field of anti-jamming; Interacting with an unknown environment, obtaining feedback rewards, and then modifying its strategy to ma...

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): G01S7/36G06F30/27G06K9/62
CPCG01S7/36G06F30/27G06F2119/02G06F18/214Y02A90/10
Inventor 孙国皓江秀强季袁冬钟苏川张应奎
Owner SICHUAN 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