基于Q-学习的智能雷达对抗

doi:10.3969/j.issn.1001-506X.2018.05.11

系统工程与电子技术 ›› 2018, Vol. 40 ›› Issue (5): 1031-1035.doi: 10.3969/j.issn.1001-506X.2018.05.11

基于Q-学习的智能雷达对抗

邢强¹, 贾鑫², 朱卫纲²

1. 航天工程大学研究生管理大队, 北京 101416; 2. 航天工程大学电子与光学工程系, 北京 101416

出版日期:2018-04-28 发布日期:2018-04-24

Intelligent radar countermeasure based on Q-learning

XING Qiang¹, JIA Xin², ZHU Weigang²

1. Department of Graduate Management, Space Engineering University, Beijing 101416, China; 2. Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China

Online:2018-04-28 Published:2018-04-24

摘要/Abstract

摘要：

随着雷达技术的进步,雷达发展趋于多功能与智能化,抗干扰能力增强,应用于常规雷达的对抗方法作战效能下降,针对多功能雷达,尤其是工作模式未知的智能对抗成为雷达对抗领域的热点与难点。基于此,该文阐述了智能雷达对抗(intelligent radar countermeasure, IRC)方法,对比了智能雷达对抗与传统雷达对抗(traditional radar countermeasure, TRC)的区别。介绍了强化学习(reinforcement learning, RL)基本原理,针对雷达工作模式及数目未知情况,提出了基于Q-学习的智能雷达对抗方法,给出了算法步骤,分析了Q矩阵收敛时间、收敛值与循环次数的关系。仿真实验表明:给定仿真实验条件下,智能化雷达对抗Q矩阵收敛时间仅为秒量级,能根据干扰效果自主学习并智能决策,提高了雷达对抗系统的实时性与自适应性,且能同时对抗多工作模式的雷达。

Abstract:

With the progress of radar technology, the development of radar tends to multifunction and intellectualization. The anti-jamming capability of radar is enhanced, and the combat effectiveness of the radar countermeasure method for conventional radar is decreasing. The countermeasure method for multifunction radar, especially for a number of working modes unknown, has become the hotspot and difficulty of research. Based on this, this paper expounds the intelligent radar countermeasure (IRC) method, and compares the difference between IRC and traditional radar countermeasure (TRC). The basic principle of reinforcement learning (RL) is introduced. For the situation with a number of working modes unknown, IRC based on Q-learning is proposed, and the algorithm steps are given. The relationship between the convergence time, the convergence value and the cycle times of the Q matrix is analyzed. Simulation results show that the Q matrix convergence time is only the second magnitude under the given simulation experiment condition. The radar countermeasure system can learn independently and make decision according to the jamming effect, which improves the real-time performance and adaptability, and can resist the multi-working mode radar simultaneously.

邢强, 贾鑫, 朱卫纲. 基于Q-学习的智能雷达对抗[J]. 系统工程与电子技术, 2018, 40(5): 1031-1035.

XING Qiang, JIA Xin, ZHU Weigang. Intelligent radar countermeasure based on Q-learning[J]. Systems Engineering and Electronics, 2018, 40(5): 1031-1035.

基于Q-学习的智能雷达对抗

Intelligent radar countermeasure based on Q-learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价