基于RS-DBN的电子对抗目标清单生成方法

doi:10.12305/j.issn.1001-506X.2021.09.01

摘要/Abstract

摘要：

由于电子对抗作战目标类型和工作方式多样, 变化速度快, 有效信息难以充分获得, 且在不同作战阶段呈现出不同特点, 使用传统评估方法难以对其等级排序实施精确评估。对此, 提出一种基于随机集的动态贝叶斯网络电子对抗目标等级评估方法。首先，对电子对抗作战目标清单生成方式进行梳理, 确定了评价指标体系, 并根据作战阶段的变化特点，结合动态贝叶斯网络完善了评价体系。然后, 充分考虑作战过程中数据获取不完整的特点, 通过引入随机集方法将传统贝叶斯网络的节点参数求解方法进行拓展, 使用区间数学的思想得到了较为准确的动态贝叶斯网络节点参数。最后，进行了案例仿真计算和结果分析, 并对节点概率确定方法进行算法复杂度讨论。结果表明，所提方法更加适合样本不完整的军事评估问题, 评估结果与实际作战基本一致, 使用的算法具有高效性、适用性和推广性。

关键词: 电子对抗, 动态贝叶斯网络, 随机集, 区间数学, 目标清单

Abstract:

Because the types and working methods of electronic countermeasures are diverse and change rapidly, effective information is difficult to obtain completely, and different operational characteristics are presented in different operational stages, so it is difficult to accurately evaluate their ranking by using traditional evaluation methods. Therefore, a target level evaluation method of electronic countermeasures based on random set dynamic Bayesian network is proposed. Firstly, the generation method of electronic countermeasures combat target list is combed, the evaluation index system is determined, and the evaluation system is improved based on the changing characteristics of the combat stage combined with the dynamic Bayesian network. Then, after fully consider the characteristics of incomplete data acquisition in combat, the traditional method of solving node parameters of Bayesian network is extended through the introduction of the random set method, and the more accurate node parameters of dynamic Bayesian network are obtained by using the idea of interval mathematics. Finally, the simulation calculation and result analysis of an example are carried out, and the complexity of the algorithm is discussed by the method of determining the node probability. The results show that the method proposed in this paper is more suitable for military evaluation with incomplete samples, and the evaluation results are basically consistent with actual combat situation. The algorithm used are efficient, applicable and popular.

Key words: electronic warfare, dynamic Bayesian network, random set, interval mathematics, target list

中图分类号:

E837
E917

赵禄达, 王斌. 基于RS-DBN的电子对抗目标清单生成方法[J]. 系统工程与电子技术, 2021, 43(9): 2373-2382.

Luda ZHAO, Bin WANG. Method of electronic countermeasure targets' list generation based on RS-DBN[J]. Systems Engineering and Electronics, 2021, 43(9): 2373-2382.

图/表 19

图1

图2

图3

表1

图4

图5

表2

表3

表4

表5

图6

表6

表7

表8

图7

表9

图8

图9

表10

参考文献 31

1	刘庆国. 电子对抗作战指挥系统研究[M]. 北京: 国防大学出版社, 2011.
	LIU Q G . Research on electronic countermeasures operational command system[M]. Beijing: National Defense University Press, 2011.
2	奚之飞, 徐安, 寇英信, 等. 基于灰主成分的空战目标威胁评估[J]. 系统工程与电子技术, 2021, 43 (1): 147- 155.
	XI Z F , XU A , KOU Y X , et al. Air combat target threat assessment based on gray principal component[J]. System Engineering and Electronic Technology, 2021, 43 (1): 147- 155.
3	ZHANG K, LIU P P, LI K, et al. Multi-target threat assessment in air combat based on AHP and FVIKOR[C]//Proc. of the IEEE International Conference on Unmanned Systems, 2017.
4	奚之飞, 徐安, 寇英信, 等. 基于前景理论的空战目标威胁评估[J]. 兵工学报, 2020, 41 (6): 1236- 1248.
	XI Z F , XU A , KOU Y X , et al. Threat evaluation of air combat targets based on prospect theory[J]. Acta Armamentarii, 2020, 41 (6): 1236- 1248.
5	XU X M, YANG R N, YANG Y. Threat assessment in air combat based on elm neural network[C]//Proc. of the IEEE International Conference on Artificial Intelligence and Computer Applications, 2019.
6	ZHANG S L, ZHANG T, XU X M. Threat estimation of aerial target based on extreme learning machine[C]//Proc. of the Chinese Control Conference, 2019.
7	张永利, 潘哲, 刘楠楠. 基于离散Hopfield神经网络的辐射源目标威胁估计[J]. 指挥信息系统与技术, 2020, 11 (2): 39- 43, 48.
	ZHANG Y L , PAN Z , LIU N N . The threat estimation of radiation source target based on discrete Hopfield neural network[J]. Command Information System and Technology, 2020, 11 (2): 39- 43, 48.
8	SUN H W , XIE X F . Threat evaluation method of warships formation air defense based on AR(p)-DITOPSIS[J]. Journal of Systems Engineering and Electronics, 2019, 30 (2): 297- 307. doi: 10.21629/JSEE.2019.02.09
9	侯思尧, 李永光, 陈思静, 等. 利用主客观集成赋权法的多目标威胁评估[J]. 电讯技术, 2019, 59 (8): 956- 961. doi: 10.3969/j.issn.1001-893x.2019.08.016
	HOU S Y , LI Y G , CHEN S J , et al. Multi-target threat assessment using subjective and objective integrated weightingmethod[J]. Telecommunication Technology, 2019, 59 (8): 956- 961. doi: 10.3969/j.issn.1001-893x.2019.08.016
10	FENG J F , ZHANG Q , HU J H , et al. Dynamic assessment method of air target threat based on improved GIFSS[J]. Journal of Systems Engineering and Electronics, 2019, 30 (3): 525- 534. doi: 10.21629/JSEE.2019.03.10
11	刘昊, 邢岩, 吴世杰. 基于体系破击的联合火力打击目标价值评估[J]. 系统工程与电子技术, 2020, 42 (12): 2802- 2810. doi: 10.3969/j.issn.1001-506X.2020.12.17
	LIU H , XING Y , WU S J . Value evaluation of joint fire strike target based on system destruction[J]. System Engineering and Electronics, 2020, 42 (12): 2802- 2810. doi: 10.3969/j.issn.1001-506X.2020.12.17
12	汪鑫, 龙光正, 汪志宏, 等. 基于灰色聚类和序关系的防空保卫目标排序研究[J]. 弹箭与制导学报, 2018, 38 (2): 25- 29.
	WANG X , LONG G Z , WANG Z H , et al. Research on air defense target sequencing based on grey clustering and order relation[J]. Journal of Projectiles and Guidance, 2018, 38 (2): 25- 29.
13	孙海文, 谢晓方, 孙涛, 等. 小样本数据缺失状态下DBN舰艇编队防空目标威胁评估方法[J]. 系统工程与电子技术, 2019, 41 (6): 1300- 1308.
	SUN H W , XIE X F , SUN T , et al. The threat assessment method of DBN fleet air defense targets under the state of small sample data missing[J]. System Engineering and Electronics, 2019, 41 (6): 1300- 1308.
14	WANG X , ZUO J Z , YANG R N , et al. Target threat assessment based on dynamic bayesian network[J]. Journal of Physics: Conference Series, 2019, 1302 (4): 042023.
15	MA S D , ZHANG H Z , YANG G Q . Target threat level assessment based on cloud model under fuzzy and uncertain conditions in air combat simulation[J]. Aerospace Science and Technology, 2017, 67, 49- 53. doi: 10.1016/j.ast.2017.03.033
16	陈怀进, 刘雅奇, 和伟, 等. 基于DBN的雷达干扰目标选择方法[J]. 现代雷达, 2014, 36 (9): 6- 10. doi: 10.3969/j.issn.1004-7859.2014.09.002
	CHEN H J , LIU Y Q , HE W , et al. The method of radar jamming target selection based on DBN[J]. Modern Radar, 2014, 36 (9): 6- 10. doi: 10.3969/j.issn.1004-7859.2014.09.002
17	MENG G L, ZHOU M Z, ZHANG H M, et al. Threat assessment for rotte based on cooperative tactical recognition[C]//Proc. of the IEEE International Conferences on Ubiquitous Computing & Communications and Data Science and Computational Intelligence and Smart Computing, Networking and Services, 2019.
18	XU Y H, CHENG S Y, ZHANG H B, et al. Air target combat intention identification based on IE-DSBN[C]//Proc. of the International Workshop on Electronic Communication and Artificial Intelligence, 2020.
19	全军军事委员会. 中国人民解放军军语[M]. 北京: 军事科学出版社, 2011.
	Military Committee of the Army . Military Language of the Chinese People's Liberation Army[M]. Beijing: Military Science Press, 2011.
20	张明双, 徐克虎, 李灵之. 合成旅目标威胁评估指标体系[J]. 火力与指挥控制, 2019, 44 (12): 108- 113. doi: 10.3969/j.issn.1002-0640.2019.12.022
	ZHANG M S , XU K H , LI L Z . Synthetic brigade target threat assessment index system[J]. Fire Power & Command Control, 2019, 44 (12): 108- 113. doi: 10.3969/j.issn.1002-0640.2019.12.022
21	DZIADOSZ A, BANACH D, MESZEK W, et al. Impact of the adopted strategy on the result of multi-criteria analysis of technology solution based on AHP (BOCR)[C]//Proc. of the MATEC Web of Conferences, 2018.
22	李世楷. 随机集与集值鞅[M]. 贵阳: 贵州科技出版社, 1994.
	LI S K . Random set and set-valued martingale[M]. Guiyang: Guizhou Science and Technology Press, 1994.
23	DUBOIS D , HENRI P . A set-theoretic view of belief functions[J]. Classic Works of the Dempster-Shafer Theory of Belief Functions, 2008, 12, 375- 410.
24	WANG L , WANG X S , YU J Z . Quasi-shadowing property on random partially hyperbolic sets[J]. Acta Mathematica Sinica, 2018, 34 (9): 1429- 1444. doi: 10.1007/s10114-018-7314-4
25	YANG J B , XU D L . Evidential reasoning rule for evidence combination[J]. Artificial Intelligence, 2013, 20 (5): 1- 29.
26	DU Y W , WANG Y M , QIN M . New evidential reasoning rule with both weight and reliability for evidence combination[J]. Computers & Industrial Engineering, 2018, 124, 493- 508.
27	GOODMAN I R , MAHLER R P , NGUYEN H T . Mathema-tics of data fusion[M]. Berlin: Springer Netherlands, 1997.
28	邵国培, 曹志耀, 何俊. 电子对抗作战效能分析原理[M]. 北京: 军事科学出版社, 2013.
	SHAO G P , CAO Z Y , HE J . Principles of effectiveness analysis of electronic countermeasures[M]. Beijing: Military Science Press, 2013.
29	冯泽彪, 汪建均, 马义中. 基于多变量高斯过程模型的贝叶斯建模与稳健参数设计[J]. 系统工程理论与实践, 2020, 40 (3): 703- 713.
	FENG Z B , WANG J J , MA Y Z . Bayesian modeling and robust parameter design based on multivariable Gaussian process model[J]. System Engineering Theory and Practice, 2020, 40 (3): 703- 713.
30	AKINORI H , KENJI W , TAKIO K . Sparse discriminant analysis based on estimation of posterior probabilities[J]. Journal of Applied Statistics, 2019, 46 (15): 2761- 2785. doi: 10.1080/02664763.2019.1613348
31	SPRENT P , SMEETON N C . Applied nonparametric statistical methods[M]. Boca Raton: CRC press, 2016.

节点	状态空间	状态字母代号
目标等级	{一级, 二级, 三级}	{One, Two, Three}
RIS	{高, 中, 低}	{High, Middle, Low}
VAL	{高, 中, 低}	{High, Middle, Low}
DEF	{高, 中, 低}	{High, Middle, Low}
JAM	{高, 中, 低}	{High, Middle, Low}
INF	{高, 中, 低}	{High, Middle, Low}
ENV	{高, 中, 低}	{High, Middle, Low}
UNF	{高, 中, 低}	{High, Middle, Low}
GRA	{一级, 二级, 三级}	{One, Two, Three}
MIN	{高, 中, 低}	{High, Middle, Low}
ADD	{高, 中, 低}	{High, Middle, Low}
THR	{高, 中, 低}	{High, Middle, Low}

X	P(RIS\|X)			P(value\|X)
X	high	middle	low	high	middle	low
One	70	25	5	672	25	78
Two	60	25	15	66	25	9
Three	60	25	15	75	15	10

RIS	P(DEF \| RIS)			P(INF \| RIS)
RIS	high	middle	low	high	middle	low
high	55.323	23.56	21.117	12.46	34.56	52.98
middle	46.456	41.47	12.08	46.65	23.46	29.89
low	53.345	32.67	13.99	24.46	45.57	29.97

value	P(UNF \| value)			P(GRA \| value)			P(MIN \| value)			P(THR \| value)
value	high	middle	low	One	Two	Three	high	middle	low	high	middle	low
high	66.56	24.56	8.88	60	20	20	60	30	10	61.25	22.43	16.32
middle	45.457	45.567	8.976	50	20	30	50	20	30	18.88	29.56	51.56
low	53.45	23.45	23.1	40	22	38	40	20	40	23.67	22.18	54.15

划分区间	[0, 0.1)	[0.1, 0.2)	[0.2, 0.3)	[0.3, 0.4)	[0.4, 0.5)	[0.5, 0.6)	[0.6, 0.7)	[0.7, 0.8)	[0.8, 0.9)	[0.9, 1.0]
ξ_JAM	0.004 18	0.003 26	0.002 29	0.001 31	0.000 30	0.000 71	0.001 71	0.002 68	0.003 63	0.004 54
ξ_ENV	0.134 92	0.116 71	0.100 97	0.087 34	0.075 56	0.065 37	0.056 55	0.048 92	0.042 32	0.036 61