Game-oriented radar countermeasure strategy generation method

A countermeasure and radar technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as being unable to cope with changing opponents and unable to win

Active Publication Date: 2020-06-12
中国人民解放军32802部队 +1
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The existing radar confrontation game mainly studies the two-player zero-sum game with static complete information. Both opponents have a complete understanding of the opponent's action space and profit function, and the final confrontation strategy is also fixed. However, in the actual complex electromagnetic environment , this static strategy cannot cope with changing opponents, and it is easy for opponents to speculate on their own strategies, so that they cannot win in the confrontation

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
  • Game-oriented radar countermeasure strategy generation method
  • Game-oriented radar countermeasure strategy generation method
  • Game-oriented radar countermeasure strategy generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0050] In this experiment, the confrontation scenario is set as a one-to-one confrontation, which includes a switchable multifunctional radar and a jammer that can change the jamming pattern. Set N radar = 3, that is, the radar has three working states, denoted as s 0 ~s 2 , where the radar chooses different working states to choose different actions; N jam = 5, that is, the interfering party has five interference styles, denoted as j 0 ~j 4 , similarly, the interference party chooses different interference styles to choose different actions. Set the number of iterations N iter =1000, the number of traversals of the game tree in each iteration K=10, the training frequency of th...

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 game-oriented radar countermeasure strategy generation method, which comprises the following steps: setting a countermeasure scene: setting a radar and an interference systemas two players, constructing a radar countermeasure game tree, setting two neural networks of a regret value and a countermeasure strategy and a corresponding cache region for each player, and initializing neural network parameters; traversing the K game trees within the iteration times, alternately training the radar and the interference party, training the regret value neural network by using the regret value cache region data, and then training the adversarial strategy neural network of the radar and the interference party by using the collected adversarial strategy cache region data untilthe adversarial strategy neural network converges. Compared with radar countermeasure static game research, the method has the advantages that a dynamic game model of incomplete information is constructed, Nash equilibrium of radar and interference system games is approximately solved by using a neural network under the condition that both parties are intelligent, and respective Nash equilibrium strategies are obtained through multiple times of dynamic iterative updating.

Description

technical field [0001] The invention relates to the cross-technical field of radar electronic countermeasures, game theory and artificial intelligence, in particular to a game-oriented radar countermeasure generation method. Background technique [0002] The application of artificial intelligence technology in the field of electronic countermeasures is getting more and more in-depth, and radar countermeasures are also becoming more intelligent. Both radar and jamming systems have developed intelligent algorithms with adaptive and even cognitive capabilities. Research on radar from the perspective of dynamic games between the two parties The problem of electronic countermeasures is an important development direction. [0003] At present, the field of cognitive electronic countermeasures mainly focuses on the unilateral intelligent algorithm research of radar or jammer, such as waveform optimization, target detection, identification and tracking technology of cognitive radar; ...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 杨健王沙飞李岩肖德政田震张丁
Owner 中国人民解放军32802部队
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