Radar anti-interference intelligent decision-making method based on reinforcement learning

An intelligent decision-making and reinforcement learning technology, applied in radio wave measurement systems, instruments, etc., can solve the problems of single LFM waveform design method and cannot deal with complex interference scenarios, and achieve low decision-making time, interference suppression, and high decision-making accuracy. Effect

Pending Publication Date: 2021-11-09
HARBIN INST OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the LFM waveform design method in the existing radar anti-jamming method is single and cannot deal with com

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 anti-interference intelligent decision-making method based on reinforcement learning
  • Radar anti-interference intelligent decision-making method based on reinforcement learning
  • Radar anti-interference intelligent decision-making method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0069] Specific implementation mode 1. Combination figure 1 As shown, the present invention provides a radar anti-jamming intelligent decision-making method based on reinforcement learning, including,

[0070] For each confrontation round between the radar and the jammer, the radar transmitting end transmits the LFM waveform based on the frequency modulation slope disturbance to the electromagnetic interference environment, and the radar receiving end receives the echo signal from the electromagnetic interference environment; the echo signal includes Target echo signal and interference echo signal;

[0071] A three-step matched filter interference suppression method is used for the echo signal to achieve the effect of distinguishing the target from the interference and obtain the target echo signal;

[0072] According to the waveform performance of the transmitted LFM waveform and the anti-jamming performance of the receiving end after interference suppression, the radar anti...

specific Embodiment 1

[0168] Using the direct target matched filtering method as method 0 and the three-step matched filtering based interference suppression method designed by the present invention to process the simulation data, and compare the interference suppression effect.

[0169] The simulation parameters are set as follows:

[0170] The radar transmits an LFM signal based on frequency modulation slope disturbance. The pulse width of the reference signal is 90μs, the bandwidth is 5MHz, and the frequency modulation slope is The 30μs sampling rate is 70MHz, and the target distance is 3km from the radar. The jammer implements distance false target deception jamming, and continuously retransmits the radar intercepted signal of the previous pulse repetition period. A false target distance deception jamming delay is 1 μs, and the jamming limit threshold is the maximum value after the pulse compression of the target signal.

[0171] Jamming Scenario 1 Setting: Deceptive jamming only forwards the...

specific Embodiment 2

[0174] Using the frequency modulation slope random disturbance method (method 1) and the intelligent decision-making method based on Q-learning designed by the present invention (method 2) to process the simulation data, and compare the anti-jamming decision-making effects.

[0175] The simulation parameters are set as follows:

[0176] The same simulation parameters as in Embodiment 1 are used. Taking the pulse signal of two LFM waveforms continuously transmitted as an example, they are recorded as waveform 1 and waveform 2 in turn, and the value ranges of the frequency modulation slopes are respectively Take 26 frequency points at equal intervals in the value range to form the radar action space, so the radar action set contains 26×26=676 actions in total. Setting Reinforcement Learning Parameters: Thresholds in the Reward Function¶ 1 = -13.5dB, γ 2 =-17dB, γ 3 = 20dB; the weight ω in the reward function 1 = 1, ω 2 = 1, ω 3 =1 / 6; greedy probability ε=0.1; learning ra...

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 anti-interference intelligent decision-making method based on reinforcement learning, and belongs to the technical field of radar anti-interference. The invention aims to solve the problem that the design method of the LFM waveform in the existing radar anti-interference method is single and cannot deal with complex interference scenes. The method comprises the following steps: for each adversarial round of a radar and a jammer, transmitting an LFM waveform based on frequency modulation slope disturbance to an electromagnetic interference environment at a radar transmitting end, and receiving an echo signal at a radar receiving end; using a three-step matched filtering interference suppression method for the echo signal, and obtaining a target echo signal; setting a radar anti-interference decision criterion; judging whether the target echo signal meets a decision criterion or not, and if yes, realizing radar anti-interference; otherwise, on the basis of the decision criterion, calculating the LFM waveform parameter of the next adversarial round by adopting a radar online anti-interference intelligent decision algorithm, and generating a new LFM waveform through the radar transmitting end. The method is used for realizing online anti-interference decision.

Description

technical field [0001] The invention relates to a radar anti-jamming intelligent decision-making method based on reinforcement learning, and belongs to the technical field of radar anti-jamming. Background technique [0002] Facing the increasingly complex electromagnetic environment, the anti-jamming ability of radar has been paid more and more attention by researchers. [0003] The jamming system based on digital radio frequency memory (DRFM) implements jamming by duplicating or intra-pulse adjustment of the radar transmission signal. Because of its strong coherence, the threat to radar is increasing. Especially in the face of scenarios where interference parameters change dynamically, transmitting linear frequency modulation (LFM) signals with fixed parameters can no longer meet the requirements of anti-interference. [0004] The existing anti-jamming method based on the LFM waveform design based on the FM slope disturbance often designs the FM slope randomly, or the FM ...

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
IPC IPC(8): G01S7/36G01S7/02
CPCG01S7/36G01S7/023
Inventor 许荣庆魏晶晶于雷位寅生
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