Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2022, Vol. 56 Issue (1): 75-83    DOI: 10.3785/j.issn.1008-973X.2022.01.008
计算机技术、信息与电子工程     
基于信息共享的多智能体自主电子干扰系统
张盼1,2(),丁华3,张颖而4,李冰凝5,皇甫江涛4,金仲和1,2,*()
1. 浙江大学 微小卫星研究中心, 浙江 杭州 310027
2. 浙江省微纳卫星研究重点实验室, 浙江 杭州 310027
3. 战略支援部队 航天系统装备部, 北京 100094
4. 浙江大学 信息与电子工程学院, 浙江 杭州310027
5. 中国西安卫星测控中心, 浙江 杭州 310000
Multi-agent autonomous electronic jamming system based on information sharing
Pan ZHANG1,2(),Hua DING3,Ying-er ZHANG4,Bing-ning LI5,Jiang-tao HUANG-FU4,Zhong-he JIN1,2,*()
1. Micro-Satellite Research Center, Zhejiang University, Hangzhou 310027, China
2. Zhejiang Key Laboratory of Micro-nano Satellite Research, Hangzhou 310027, China
3. Aerospace Equipment Department, PLA Strategic Support Force, Beijing 100094, China
4. College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
5. Xi'an Satellite Control Center, Hangzhou 310000, China
 全文: PDF(1249 KB)   HTML
摘要：

为了实现电子干扰机在复杂电磁环境中对辐射源的有效干扰，利用多智能体电子干扰机与信息共享机制，突破原有单传感器的有限信息感知能力，实现实时动态态势信息共享，增强电子干扰机的智能决策认知能力. 基于信息共享的多智能体自主电子干扰系统实现了μs级的干扰参数快速收敛，减小了单传感器的信息误差概率. 通过仿真实验表明，基于该方法的干扰参数更新策略随着态势环境的动态变化而实时自主调整，实现了更加自主与智能的认知电子干扰系统.
关键词： 信息共享;  多智能体电子干扰机;  Q-Learning;  态势感知    
Abstract:

Multi-agent electronic jammers and information sharing mechanism was used to break through the limited information perception ability of the original single sensor in order to realize the effective jamming of radiation source in complex electromagnetic environment. Then real-time dynamic situation information sharing was realized, and the intelligent decision cognition ability of electronic jammer was enhanced. The rapid convergence of the microsecond-level about the jamming parameters was achieved by the multi-agent independent electronic jamming system based on information sharing, and the information error probability in a single-jammer conditions was reduced. The experimental results show that the jamming parameter update strategy based on the method is adjusted in real time with the dynamic change of situational environment. A more autonomous and intelligent cognitive electronic jamming system is realized.
Key words: information sharing    multi-agent electronic jammer    Q-Learning    situational awareness
收稿日期: 2021-03-15 出版日期: 2022-01-05
CLC:  TN 959  
基金资助: 国家杰出青年科学基金资助项目(61525403)；省级重点研发计划资助项目（209C05004）；之江国际青年人才基金资助项目
通讯作者: 金仲和     E-mail: zhangpan_zju@zju.edu.cn;jinzh@zju.edu.cn
作者简介: 张盼(1993—)， 男，博士生，从事智能信息感知、信号处理的研究. orcid.org/0000-0002-9818-1043. E-mail: zhangpan_zju@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
张盼
丁华
张颖而
李冰凝
皇甫江涛
金仲和

引用本文:

张盼,丁华,张颖而,李冰凝,皇甫江涛,金仲和. 基于信息共享的多智能体自主电子干扰系统[J]. 浙江大学学报(工学版), 2022, 56(1): 75-83.

Pan ZHANG,Hua DING,Ying-er ZHANG,Bing-ning LI,Jiang-tao HUANG-FU,Zhong-he JIN. Multi-agent autonomous electronic jamming system based on information sharing. Journal of ZheJiang University (Engineering Science), 2022, 56(1): 75-83.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2022.01.008    或    https://www.zjujournals.com/eng/CN/Y2022/V56/I1/75

图 1  传统电子干扰方法
图 2  电子对抗干扰模型
图 3  辐射源电磁参数侦察流程
图 4  基于环境交互的动态电子干扰策略
图 5  基于信息共享的多智能体联合态势感知
阶段 fc/GHz wp/μs fPR/Hz Bw/MHz
T0 3.25 22.5 5 000 10
T1 5 60 10 000 10
T2 4.375 40 5 000 20
T3 2.6 50 2 500 20
T4 5.45 20 10 000 15
T5 6.25 35 5 000 15
表 1  辐射源电磁态势变化表
图 6  多智能体协同感知自主干扰的流程图
图 7-1  
图 7  多智能体电子干扰机测量不同时刻的电磁态势信息
阶段 fc/GHz wp/μs PRI/μs k / (1011Hz · s?1)
T0 3.2539 22.367 198.30 4.4920
T1 4.9758 59.76 102.760 1.6340
T2 4.3863 40.432 200.843 4.9317
T3 2.6036 50.372 399.346 3.9705
T4 5.4620 19.874 100.264 7.5475
T5 6.2510 35.006 201.149 4.2850
表 2  信息共享后的辐射源信号参数估计
图 8  一个周期内的奖励回报曲线
图 9  一个周期内的损失曲线
图 10  干扰参数矩阵随时间的动态响应曲线图
图 11  辐射源态势信息的感知准确率随智能体数量变化的曲线
1 李振初 人工智能技术在电子战中的应用[J]. 电子对抗技术, 1988, (2): 31- 43
LI Zhen-chu Application of AI technology in EW[J]. Electronic Warfare Technology, 1988, (2): 31- 43
2 MENG Xiang-ping, GAO Yan. Electric systems analysis [M]. Beijing: Higher Education Press, 2004: 3-21.
3 ZHENG X L, LIU J H, WANG B S Analysis of range_doppler coherent jamming performance against radar with the RATR technique[J]. Electronic Information Warfare Technology, 2017, 32 (5): 52- 56
4 ZHAO Y L, WANG X S, WANG G Y Tracking technique for radar network in the presence of multi-range-false-target deception jamming[J]. Acta Electronic Sinica, 2007, 3 (3): 454- 458
5 LOPATKA J, KULPA K, SZCZEPANKIEWICZ M, et al. Cognitive systems in electronic warfare[C]// XI Conference on Reconnaissance and Electronic Warfare Systems. Oltarzew: [s.n.], 2017: 1041802.
6 KINGSLEY N, GUERCI J R. Adaptive amplifier module technique to support cognitive RF architectures[C]// Radar Conference.[S.l.]: IEEE, 2014.
7 DARPA. Behavior learning for adaptive electronic warfare [EB/OL]. (2010-10-06). https://www.fbo.gov.
8 DARPA. Adaptive radar countermeasures [EB/OL]. (2012-08-27). https://www.fbo.gov.
9 王沙飞, 鲍雁飞, 李岩 认知电子战体系结构与技术[J]. 中国科学: 信息科学, 2018, 48 (12): 1603- 1613
WANG Sha-fei, BAO Yan-fei, LI Yan The architecture and technology of cognitive electronic warfare[J]. Scientia Sinica: Informationis, 2018, 48 (12): 1603- 1613
doi: 10.1360/N112018-00153
10 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 Wei-gang Intelligent radar countermeasure based on Q-learning[J]. Systems Engineering and Electronics, 2018, 40 (5): 1031- 1035
doi: 10.3969/j.issn.1001-506X.2018.05.11
11 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 Yun-jie, ZHU Yun-peng, GAO Mei-guo Design of cognitive radar jamming based on Q-learning algorithm[J]. Transactions of Beijing Institute of Technology, 2015, 35 (11): 1194- 1199
12 HAO T, CUI C, GONG Y Efficient low-PAR waveform design method for extended target estimation based on information theory in cognitive radar[J]. Entropy, 2019, 21 (3): 261
doi: 10.3390/e21030261
13 SU H, CHEN M Z Q Multi-agent containment control with input saturation on switching topologies[J]. IET Control Theory and Applications, 2015, 9 (3): 399- 409
doi: 10.1049/iet-cta.2014.0393
14 FU J, WAN Y, WEN G, et al Distributed robust global containment control of second-order multiagent systems with input saturation[J]. IEEE Transactions on Control of Network Systems, 2019, 6 (4): 1- 10
doi: 10.1109/TCNS.2019.2956892
15 YAN Y, HUANG J Cooperative output regulation of discrete-time linear time-delay multi-agent systems under switching network[J]. Neurocomputing, 2017, 241 (7): 108- 114
16 YAN Y, HUANG J Cooperative output regulation of discrete-time linear time-delay multi-agent systems[J]. IET Control Theory Appliance, 2016, 10 (16): 2019- 2026
doi: 10.1049/iet-cta.2016.0106
17 LI Z, REN W, LIU X, et al Distributed containment control of multi-agent systems with general linear dynamics in the presence of multiple leaders[J]. International Journal of Robust and Nonlinear Control, 2013, 23 (5): 534- 547
doi: 10.1002/rnc.1847
18 BUI V H, NGUYEN T T, KIM H M. Distributed operation of wind farm for maximizing output power: a multi-agent deep reinforcement learning approach [J]. Access IEEE, 2020, 8: 173136-173146.
19 何俊辉. 侦察干扰一体化处理器FPGA软件设计[D]. 哈尔滨: 哈尔滨工程大学, 2017.
HE Jun-hui. FPGA software design for reconnaissance and jamming integration processor [D]. Harbin: Harbin Engineering University, 2017.
[1] 林小夏,张树有,陈婧,赵振. 多体动力学与有限元联合仿真的时变载荷历程模型[J]. J4, 2011, 45(9): 1643-1649.