[1]雷震烁,刘松涛,陈奇.基于SVM-DS融合的干扰效果在线评估方法[J].探测与控制学报,2020,42(03):92.[doi:.]
 LEI Zhenshuo,LIU Songtao,CHEN Qi.An Online Jamming Effect Evaluation Method Based on SVM-DS Fusion[J].,2020,42(03):92.[doi:.]
点击复制

基于SVM-DS融合的干扰效果在线评估方法()
分享到:

《探测与控制学报》[ISSN:1008-1194/CN:61-1316/TJ]

卷:
42
期数:
2020年03
页码:
92
栏目:
出版日期:
2020-06-15

文章信息/Info

Title:
An Online Jamming Effect Evaluation Method Based on SVM-DS Fusion
文章编号:
1008-1194(2020)03-0092-07
作者:
雷震烁刘松涛陈奇
海军大连舰艇学院信息系统系,辽宁 大连 116018
Author(s):
LEI Zhenshuo LIU Songtao CHEN Qi
Department of Information System, Dalian Naval Academy, Dalian 116018, China
关键词:
干扰效果在线评估支持向量机DS证据理论多特征融合
Keywords:
jamming effect online evaluation support vector machine DS evidence theory multi-feature fusion
分类号:
TN974
DOI:
.
文献标志码:
A
摘要:
当舰载电子对抗系统对敌方反舰导弹末制导雷达实施干扰后,需根据干扰效果调整干扰样式或采取硬抗击行动,因此如何实时且准确地进行干扰效果在线评估对提高舰艇反导防御能力具有重要意义。提出一种基于SVM-DS融合的干扰效果在线评估方法,首先根据在线评估要求提取干扰方能量域行为、频域行为、时域行为以及敌方抗干扰行为4类特征参数,然后对特征参数利用支持向量机(SVM)分类,并将分类结果转化为DS证据的基本信度分配,最后根据DS证据理论的评估分数及判决门限输出在线评估结果。仿真实验表明,SVM-DS融合算法的干扰效果识别准确率达到88.9%,可较好实现干扰效果的在线评估。
Abstract:
After the shipboard electronic countermeasures system jamming the terminal guidance radar of the enemy anti-ship missile, jamming patterns need adjusted according to the jamming effects, or take the implementation of hard countermeasures. Therefore, how to evaluate the jamming effect online in real time and accurately is of great significance to improve the anti-missile defense capability of naval ships. In this paper, an online jamming effect evaluation method based on SVM-DS fusion was proposed. Firstly, 4 feature parameters were extracted according to online evaluation requirements, including energy domain behavior, frequency domain behavior and time domain behavior of jammer, and anti-jamming behavior of enemy. Then, the feature parameters were classified by support vector machine (SVM), and the classification results were converted into the basic probability assignment of DS evidence. Finally, the online evaluation results were output according to DS evidence theory’s evaluation score and decision threshold. Simulation results showed that the jamming effect recognition accuracy of SVM-DS fusion algorithm reached 88.9%, which could realize the online evaluation of jamming effect better.

参考文献/References:

[1] QIN F T, MENG J, DU J, et al. Radar jamming effect evaluation based on adaboost combined classification model[C]//The 4th IEEE international Conference on Software Engineering and Service, Beijing: IEEE, 2013: 910-913.
[2] 贾鑫, 朱卫纲, 曲卫, 等. 认知电子战概念及关键技术[J]. 装备学院学报, 2015, 26(4): 96-100.
[3] 周华吉, 张春磊. 认知电子战系统组成及实现途径探究[J].中国电子科学研究院学报, 2017, 12(5): 448-451.
[4] 夏军成, 李迪, 李超. 基于二型模糊神经网络的电子战效能评估[J]. 舰船电子对抗, 2015, 38(3): 74-76.
[5] 徐新华, 黄建冲. BP神经网络在雷达干扰效果评估中的应用[J]. 雷达科学与技术, 2008, 6(4): 251-253.
[6] 王伟, 杨俊安, 崔琳, 等. 基于支持向量机的通信干扰效果在线评估算法[J]. 电子信息对抗技术, 2017, 32(2): 51-57.
[7] 赵耀东, 徐旺. 一种基于雷达状态变化的干扰效果在线评估方法[J]. 电子信息对抗技术, 2016, 31(3): 42 -46.
[8] 蔡译锋, 甘荣兵,张京瑞.电子战效能评估中评估素材的时效性[J].电子信息对抗技术, 2016, 31(4): 68-82.
[9] 王博阳. 雷达对抗在线效能评估技术研究[D]. 西安:西安电子科技大学, 2018.
[10]林连雷.支持向量机算法及其在雷达干扰效果评估中的应用研究[D].哈尔滨:哈尔滨工业大学, 2009.
[11]刘松涛, 姜宁, 刘振兴. 舰载电子对抗干扰效果在线评估方法[J]. 电子信息对抗技术, 2016, 31(4): 63-67.
[12]马焱,赵悍东,黄鑫.基于粒子群优化支持向量机神经网络的弹丸落点预报[J].探测与控制学报,2017,39(2):124-128.
[13]Platt John C. Probabilistic output for support vector machine and comparisons to regularized likelihood methods[M]. Boston: MIT Press, 1999: 1-11.
[14]朝旭,盛怀洁,陈明建.基于D-S证据讨论的反辐射无人机群协同探索[J].探测与控制学报,2018,40(1):80-87.

相似文献/References:

[1]杨立明,韦高,蔚建利.不完整复制信号在雷达中的检测性能[J].探测与控制学报,2017,39(03):41.[doi:.]
 YANG Liming,WEI Gao,WEI Jianli.Radar Detection Performance of Partly Copied Signal[J].,2017,39(03):41.[doi:.]
[2]熊波,王栋,曾鑫,等.基于时域差分的无线电引信高功率微波干扰效果评估[J].探测与控制学报,2017,39(04):1.[doi:.]
 XIONG Bo,WANG Dong,ZENG Xin,et al.Radio Fuze HPM Jamming Effect Evaluation Based on Time Domain Difference Method[J].,2017,39(03):1.[doi:.]

备注/Memo

备注/Memo:
收稿日期:2019-12-24
基金项目:中国博士后科学基金项目资助(2015M572694;2016T90979)
作者简介:雷震烁(1996—),男,河北秦皇岛人,硕士研究生,研究方向,电子对抗技术及应用。E-mail:448051487@qq.com
更新日期/Last Update: 2020-07-15