基于PPO算法的雷达自适应跳频抗干扰技术研究

杜钰渲; 吴中杰; 宋思盛; 张军

doi:10.15892/j.cnki.djzdxb.2026.02.005

弹箭与制导学报 >

2026 , Vol. 46 >Issue 2: 162 - 171

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2026.02.005

学术文章

基于PPO算法的雷达自适应跳频抗干扰技术研究

杜钰渲 ¹^,² ,
吴中杰 ^,²^,^* ,
宋思盛 ¹ ,
张军 ²

展开

¹ 西安电子工程研究所, 陕西西安 710100
² 国防科技大学电子科学学院, 湖南长沙 410073

^* hit_wzj@163.com。

收稿日期: 2026-01-21

网络出版日期: 2026-05-09

基金资助

国家自然科学基金(62201587)

收起

PPO-based Adaptive Frequency-hopping Anti-jamming Technique for Radar

DU Yuxuan ¹^,² ,
WU Zhongjie ^,²^,^* ,
SONG Sisheng ¹ ,
ZHANG Jun ²

Expand

¹ Xi’an Electronic Engineering Research Institute, Xi’an 710100,Shaanxi, China
² College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073,Hunan, China

Received date: 2026-01-21

Online published: 2026-05-09

Fold

摘要

针对现代复杂电磁环境中,处于稳定跟踪阶段的捷变频雷达在压制干扰下难以兼顾相干积累增益与抗干扰能力的问题,提出一种基于近端策略优化的频率与驻留时间联合控制方法。首先,分析了雷达相干积累增益与被截获风险之间的制约关系,模拟了干扰机的动态组合压制行为,构建了包含信号级特征反馈的雷达抗干扰马尔可夫决策过程模型,其次,引入近端策略优化算法,设计了兼顾探测效能与生存能力的复合奖励函数,使雷达智能体能够在未知的动态博弈环境中自主学习最优策略。该策略能够根据环境反馈实时调整工作频率与驻留时长,从而最大化信干噪比。仿真结果表明,与传统策略相比,所提方法能有效规避组合压制干扰,在显著降低被干扰概率的同时大幅提升了输出信干噪比,具有较强的环境适应性与鲁棒性。

关键词： 捷变频雷达; 深度强化学习; 近端策略优化; 相干积累; 智能抗干扰

本文引用格式

杜钰渲 , 吴中杰 , 宋思盛 , 张军 . 基于PPO算法的雷达自适应跳频抗干扰技术研究[J]. 弹箭与制导学报, 2026 , 46(2) : 162 -171 . DOI: 10.15892/j.cnki.djzdxb.2026.02.005

Abstract

To address the challenge that the frequency-agile radars in the stable tracking phase in modern complex electromagnetic environments struggle have difficulty in balancing both coherent integration gain and anti-jamming capability under blanket jamming,this paper proposes a joint control method for frequency and dwell time based on proximal policy optimization (PPO).Firstly,the trade-off relationship between radar coherent integration gain and intercept risk is analyzed.The dynamic combined jamming behavior of jammers is modeled,and a Markov decision process model for radar anti-jamming,incorporating signal-level feature feedback,is constructed.Secondly,the PPO algorithm is introduced.A compound reward function that takes into account both detection performance and survivability is designed,enabling the radar agent to autonomously learn the optimal strategy in unknown dynamical adversarial environments.This strategy can adjust the operating frequency and dwell time in real-time based on environmental feedback to maximize the signal-to-interference-plus-noise ratio.Simulated results demonstrate that,compared to traditional strategies,the proposed strategy can effectively evade the combined blanket jamming.It significantly reduces the probability of being jammed while substantially improving the output SINR,exhibiting strong environmental adaptability and robustness.

Key words： frequency-agile radar; deep reinforcement learning; proximal policy optimization; coherent integration; intelligent anti-jamming

[an error occurred while processing this directive]

参考文献

原文顺序 | 文献年度倒序 | 文中引用次数倒序

[1]	全英汇, 方文, 沙明辉, 等. 频率捷变雷达波形对抗技术现状与展望[J]. 系统工程与电子技术, 2021, 43(11):3126-3136. DOI QUAN Y H, FANG W, SHA M H, et al. Present situation and prospects of frequency agility radar wave form countermeasures[J]. Systems Engineering and Electronics, 2021, 43(11):3126-3136.

[2]	全英汇, 方文, 高霞, 等. 捷变频雷达导引头技术现状与发展趋势[J]. 航空兵器, 2021, 28(3):1-9. QUAN Y H, FANG W, GAO X, et al. Review on frequency agile radar seeker[J]. Aero Weaponry, 2021, 28(3):1-9.

[3]	AXELSSON S R J. Analysis of random step frequency radar and comparison with experiments[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(4):890-904. DOI

[4]	HAYKIN S. Cognitive radar:a way of the future[J]. IEEE Signal Processing Magazine, 2006, 23(1):30-40.

[5]	陈舒波. 基于深度强化学习的雷达抗有源干扰决策方法研究[D]. 成都: 电子科技大学, 2025. CHEN S B. Research on radar anti-active interference decision method based on deep reinforcement learning[D]. Chengdu: University of Electronic Science and Technology of China, 2025.

[6]	刘全, 翟建伟, 章宗长, 等. 深度强化学习综述[J]. 计算机学报, 2018, 41(1):1-27. LIU Q, ZHAI J W, ZHANG Z Z, et al. A survey on deep reinforcement learning[J]. Chinese Journal of Computers, 2018, 41(1):1-27.

[7]	李云杰, 朱云鹏, 高梅国. 基于Q-学习算法的认知雷达对抗过程设计[J]. 北京理工大学学报, 2015, 35(11):1194-1199. LI Y J, ZHU Y P, GAO M G. Design of cognitive radar jamming based on Q-learning algorithm[J]. Transactions of Beijing Institute of Technology, 2015, 35(11):1194-1199.

[8]	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 Q, JIA X, ZHU W G. Intelligent radar countermeasure based on Q-learning[J]. Systems Engineering and Electronics, 2018, 40(5):1031-1035.

[9]	汪浩, 王峰. 强化学习算法在雷达智能抗干扰中的应用[J]. 现代雷达, 2020, 42(3):40-44. WANG H, WANG F. Application of reinforcement learning algorithms in anti-jamming of intelligent radar[J]. Modern Radar, 2020, 42(3):40-44.

[10]	SUTTON R S, BARTO A G. Reinforcement learning:an introduction[M]. 2nd ed. Cambridge,MA,US: MIT Press, 2018.

[11]	XING Q, ZHU W G, JIA X. Research on method of intelligent radar confrontation based on reinforcement learning[C]// Proceedings of the 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA).Beijing, CN:IEEE, 2017:471-475.

[12]	LI K, JIU B, LIU H W, et al. Reinforcement learning based anti-jamming frequency hopping strategies design for cognitive radar[C]// Proceedings of the 2018 IEEE International Conference on Signal Processing,Communications and Computing (ICSPCC).Qingdao,CN:IEEE, 2018:1-5.

[13]	MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533. DOI

[14]	LI K, JIU B, LIU H W. Deep Q-network based anti-jamming strategy design for frequency agile radar[C]// Proceedings of the 2019 International Radar Conference (RADAR).Toulon, FRA:IEEE, 2019:1-5.

[15]	WANG SS, LIU Z, XIE R, et al. Reinforcement learning for compressed sensing based frequency agile radar in the presence of active interference[J]. Remote Sensing, 2022, 14(4):968. DOI

[16]	LI X Z, DONG S B. Research on efficient reinforcement learning for adaptive frequency-agility radar[J]. Sensors, 2021, 21(23):7931. DOI

[17]	AILIYA , YI W, VARSHNEY P K. , Adaptation of frequency hopping interval for radar anti-jamming based on reinforcement learning[J]. IEEE Transactions on Vehicular Technology, 2022, 71(12):12434-12449. DOI

[18]	FANG YY, ZHANG L, WEI S P, et al. Online frequency-agile strategy for radar detection based on constrained combinatorial nonstationary bandit[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(2):1693-1706.

[19]	LIU P F, LIU Y M, HUANG T Y, et al. Decentralized automotive radar spectrum allocation to avoid mutual interference using reinforcement learning[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(1):190-205. DOI

[20]	WATERS W M, LINDE G J. Frequency-agile radar signal processing[J]. IEEE Transactions on Aerospace andElectronic Systems, 1979, AES-15(3):459-464.

[21]	解烽, 刘环宇, 胡锡坤, 等. 基于复数域深度强化学习的多干扰场景雷达抗干扰方法[J]. 雷达学报, 2023, 12(6):1290-1304. XIE F, LIU H Y, HU X K, et al. A radar anti-jamming method under multi-jamming scenarios based on deep reinforcement learning in complex domains[J]. Journal of Radars, 2023, 12(6):1290-1304.

[22]	李康, 纠博, 赵宇, 等. 雷达智能博弈抗干扰技术综述与展望[J]. 现代雷达, 2023, 45(5):15-26. LI K, JIU B, ZHAO Y, et al. Overview and prospects of radar intelligent game-based anti-jamming technology[J]. Modern Radar, 2023, 45(5):15-26.

Options

文章导航