基于贝叶斯网络的空间群目标意图识别方法

doi:10.12305/j.issn.1001-506X.2026.05.20

摘要/Abstract

摘要：

针对现有空间目标意图识别方法仅适用于单一目标，难以判别空间群目标意图的问题，提出一种适用于空间群目标的意图识别方法。首先，分析空间群目标运动特性，从群内目标的编队队形、目标类型、状态层和行动层4个维度构建意图特征集。然后，研究目标连续性特征模糊化处理方法，利用数据聚类构造模糊隶属度函数，实现连续性特征隶属度的动态调整。最后，基于相对距离将场景划分为近距离和远距离两类，通过挖掘不同场景下群目标多时段特征数据，建立编队子意图与群意图之间的序列规则，利用动态序列贝叶斯网络构建空间群目标意图识别模型，并结合不同场景验证该方法的有效性和优越性。实验结果表明，所提方法与基于模糊推理的方法相比，准确率提升了12.50%，证明了所提方法的有效性。

关键词: 空间群目标, 意图识别, 贝叶斯网络, 模糊逻辑

Abstract:

Existing space target intent recognition methods are limited to single targets and struggle to distinguish the intents of space group targets. To address this issue, an intent recognition method tailored for space group targets is proposed. Firstly, the motion characteristics of space group targets are analyzed and an intent feature set is constructed based on four dimensions: formation pattern, target types, state layer, and action layer. Next, a fuzzy processing method is developed for continuous target features, employing data clustering to create fuzzy membership functions for dynamic adjustment of membership degree of continuous features. Finally, scenes are categorized into near-distance and far-distance based on relative distance. By mining multi-period feature data of group targets in different scenarios, sequential rules are established between formation sub-intents and group intents. A space group target intent recognition model is constructed using dynamic sequence Bayesian networks and its effectiveness and superiority are validated across various scenarios. Experimental results show that the proposed method improves accuracy by 12.50% compared to fuzzy reasoning-based methods, demonstrating the effectiveness of the proposed methed.

Key words: space group target, intent recognition, Bayesian network, fuzzy logic

中图分类号:

V 19

刘煊, 王肖霞, 杨风暴, 李菠, 陶映恺. 基于贝叶斯网络的空间群目标意图识别方法[J]. 系统工程与电子技术, 2026, 48(5): 1635-1646.

Xuan LIU, Xiaoxia WANG, Fengbao YANG, Bo LI, Yingkai TAO. Bayesian network-based method for space group target intent recognition[J]. Systems Engineering and Electronics, 2026, 48(5): 1635-1646.

图/表 24

图1

图2

图3

表1

图4

表2

表3

表4

图5

表5

表6

表7

图6

图7

图8

表8

图9

图10

表9

表10

表11

表12

表13

表14

参考文献 33

1	XU H F, ZHAO J J, CHEN L X, et al. A review of methods of battlefield target combat intention recognition[C]//Proc. of the International Conference on Autonomous Unmanned Systems, 2023: 3686−3696.
2	LI J S, YANG Z, LUO Y Z. Intention inference for space targets using deep convolutional neural network[J]. Advances in Space Research, 2025, 75 (2): 2184- 2200. doi: 10.1016/j.asr.2024.10.006
3	TROSO G, BONFIGLIO D, MAFFEI F, et al. Military space-advanced space command and control capability in space situational awareness[C]//Proc. of the IEEE 8th International Workshop on Metrology for Aerospace, 2021: 170−175.
4	JIA Q L, XIAO J P, ZHANG Y H, et al. Space situational awareness systems: bridging traditional methods and artificial intelligence[J]. Acta Astronautica, 2025, 228, 321- 330. doi: 10.1016/j.actaastro.2024.11.025
5	KAZEMI S, AZAD L N, SCOTT A K, et al. Orbit determination for space situational awareness: a survey[J]. Acta Astronautica, 2024, 222, 272- 295. doi: 10.1016/j.actaastro.2024.06.015
6	CAO X Y, LIU S Y, WANG H Y, et al. Spacecraft intelligent orbital game technology: a review[J]. Chinese Journal of Aeronautics, 2025, 38 (6): 103480. doi: 10.1016/j.cja.2025.103480
7	HUMBERTO B P, LAMARTINE N F. Dynamic multi-target three-way threat assessment in the context of air defense[J]. IEEE Access, 2024, 12, 141397- 141413. doi: 10.1109/ACCESS.2024.3468248
8	HUANG C, XING A J, ZENG Q L, et al. Research on autonomous decision-making method for spacecraft in the mission of rendezvous and approaching to maneuvering target based on deep reinforcement learning[J]. Asian Journal of Control, 2025, 27 (5): 2541. doi: 10.1002/asjc.3599
9	RENATO D C, CELSO M H. Reinforcement learning applied to a situation awareness decision-making model[J]. Information Sciences, 2025, 704, 121928. doi: 10.1016/j.ins.2025.121928
10	SUMAROKOV V A. On controlling the motion of an advanced manned spacecraft using jet thrusters[J]. Journal of Computer and Systems Sciences International, 2024, 63 (2): 357- 370. doi: 10.1134/S1064230724700242
11	LIU T, LI Y H. Maneuverability and agility evaluation of fighter based on beck metrics[C]//Proc. of the Asia-Pacific International Symposium on Aerospace Technology, 2024: 1545−1555.
12	李婷. 基于专家决策系统的空间战场态势感知研究[D]. 沈阳: 沈阳建筑大学, 2017.
	LI T. Research on space battlefield situational awareness based on expert decision-making systems[D]. Shenyang: Shenyang Jianzhu University, 2017.
13	CAO Y, ZHOU Z J, TANG S W, et al. On the robustness of belief-rule-based expert systems[J]. IEEE Trans. on Systems Man and Cybernetics: Systems, 2023, 53 (10): 6043- 6055. doi: 10.1109/TSMC.2023.3279286
14	陈黎, 李芳芳, 邹长虹. 基于动态贝叶斯网络和模板匹配的空中目标意图识别[J]. 现代防御技术, 2023, 51 (2): 62- 70. doi: 10.3969/j.issn.1009-086x.2023.02.008
	CHEN L, LI F F, ZHOU C H. Airborne target intent recognition based on dynamic Bayesian networks and template matching[J]. Modern Defense Technologies, 2023, 51 (2): 62- 70. doi: 10.3969/j.issn.1009-086x.2023.02.008
15	DU J H, LU D D, LI F, et al. Trajectory prediction and intention recognition based on CNN-GRU[J]. IEEE Access, 2025, 13, 26945- 26957. doi: 10.1109/ACCESS.2025.3539931
16	ZHANG C H, ZHOU Y, LI H Q, et al. STIRNet: a spatio-temporal network for air formation targets intention recognition[J]. IEEE Access, 2024, 12, 44998- 45010. doi: 10.1109/ACCESS.2024.3379410
17	WANG X Y, ZHEN Y, CHAI S Y, et al. Intelligent recognition method of target tactical behavior intention in air combat based on deep learning[J]. Engineering Applications of Artificial Intelligence, 2024, 138, 109460. doi: 10.1016/j.engappai.2024.109460
18	GUANGLEI M, RUNNAN Z, BIAO W, et al. Target tactical intention recognition in multiaircraft cooperative air combat[J]. International Journal of Aerospace Engineering, 2021, 18, 9558838. doi: 10.1155/2021/9558838
19	JIANG J X, LIU J P, LIAO X W, et al. A Bayesian network approach for dynamic behavior analysis: real-time intention recognition[J]. Information Fusion, 2025, 118, 102873. doi: 10.1016/j.inffus.2024.102873
20	ZHOU T, CHEN M, WANG Y, et al. Information entropy-based intention prediction of aerial targets under uncertain and incomplete information[J]. Entropy, 2020, 22 (3): 279. doi: 10.3390/e22030279
21	ZHANG C H, ZHOU Y, LI H, et al. Combat intention recognition of air targets based on 1DCNN-BiLSTM[J]. IEEE Access, 2023, 11, 134504- 134516. doi: 10.1109/ACCESS.2023.3337640
22	ZHANG Y, MA W C, HUANG F H, et al. A novel air target intention recognition method based on sample reweighting and attention-Bi-GRU[J]. IEEE Systems Journal, 2024, 18 (1): 501- 504. doi: 10.1109/JSYST.2023.3319643
23	TENG F, SONG Y F, GUO X P. Attention-TCN-BiGRU: an air target combat intention recognition model[J]. Mathematics, 2021, 9 (19): 2412. doi: 10.3390/math9192412
24	SUN Q B, ZHAO L R, TANG S Y, et al. Orbital motion intention recognition for space non-cooperative targets based on incomplete time series data[J]. Aerospace Science and Technology, 2025, 158, 109912. doi: 10.1016/j.ast.2024.109912
25	CHO Y, KIM J. Intent inference of ship collision avoidance behavior under maritime traffic rules[J]. IEEE Access, 2021, 9, 5598- 5608. doi: 10.1109/ACCESS.2020.3048717
26	邱钰桓. 多源信息融合的高轨目标威胁评估技术研究[D]. 南京: 南京航空航天大学, 2022.
	QIU Y H. Research on threat assessment technology for high-orbit targets based on multi-source information fusion[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2022.
27	乔殿峰, 梁彦, 马超雄, 等. 多域作战下的群目标意图识别与预测[J]. 系统工程与电子技术, 2022, 44 (11): 3403- 3412. doi: 10.12305/j.issn.1001-506X.2022.11.15
	QIAO D F, LIANG Y, MA C X, et al. Intent recognition and prediction of group targets in multi-domain operations[J]. Systems Engineering and Electronics, 2022, 44 (11): 3403- 3412. doi: 10.12305/j.issn.1001-506X.2022.11.15
28	杨锐, 杨继龙, 刘晓凡, 等. 基于动态序列贝叶斯网络的空地协同作战意图识别[J]. 指挥控制与仿真, 2024, 46 (3): 75- 85. doi: 10.3969/j.issn.1673-3819.2024.03.012
	YANG R, YANG J L, LIU X F, et al. Intent recognition of air-ground collaborative operations based on dynamic sequence Bayesian networks[J]. Command Control and Simulation, 2024, 46 (3): 75- 85. doi: 10.3969/j.issn.1673-3819.2024.03.012
29	WEI R K, SONG A Y, DUAN H X, et al. An effective procedure to build space object datasets based on STK[J]. Aerospace, 2023, 10 (3): 258. doi: 10.3390/aerospace10030258
30	YANG X, WANG J Y, DUAN S S. Scale-consistent learnable PnP network for space target pose estimation[J]. IEEE Trans. on Geoscience and Remote Sensing, 2025, 63, 5610912. doi: 10.1109/tgrs.2025.3541246
31	CHEN C H, CHOU H, HONG T P, et al. Cluster-based membership function acquisition approaches for mining fuzzy temporal association rules[J]. IEEE Access, 2020, 8, 123996- 124006. doi: 10.1109/ACCESS.2020.3004095
32	AGGARWAL S, SINGH P. Cuckoo bat and krill herd based k-means++ clustering algorithms[J]. Cluster Computing, 2019, 22 (6): 14169- 14180. doi: 10.1007/s10586-018-2262-4
33	TEBREIRO J A, LOPES A M. Computational complexity[J]. Entropy, 2017, 19 (2): 61. doi: 10.3390/e19020061

名称	状态集划分
相对速度	慢，中，快
相对距离	近，中，远
飞行方向	正向，反向
轨道阶段	抵近，保持，飞离
目标姿态	三轴稳定，自旋稳定，翻滚状态
干扰状态	开，关
编队队形	椭圆，同心双椭圆，球面，三角形，无
目标类型	探测，评估，控制

输入特征	特征状态	相对运动状态
输入特征	特征状态	逼近	绕飞	跟飞	在轨机动	远离
相对速度	慢	0.1	0.1	0.3	0.2	0.2
	中	0.3	0.8	0.6	0.7	0.3
	快	0.6	0.1	0.1	0.1	0.5
相对距离	近	0.1	0.7	0.6	0.3	0.6
	中	0.3	0.2	0.3	0.4	0.3
	远	0.6	0.1	0.1	0.3	0.1
干扰状态	开	0.5	0.8	0.7	0.5	0.5
干扰状态	关	0.5	0.2	0.3	0.5	0.5
飞行方向	正向	1	0.5	0.7	0.5	0
飞行方向	反向	0	0.5	0.3	0.5	1
目标姿态	三轴稳定	0.1	0.8	0.7	0.7	0.1
	自旋稳定	0.9	0.2	0.3	0.2	0.6
	翻滚状态	0	0	0	0.1	0.3
轨道阶段	抵近	0.6	0.1	0.2	0.1	0
	保持	0.4	0.8	0.7	0.7	0.4
	飞离	0	0.1	0.1	0.2	0.6
目标类型	探测	0.5	0.6	0.6	0.2	0.3
	评估	0.2	0.1	0.2	0.6	0.4
	控制	0.3	0.3	0.2	0.2	0.3
编队队形	椭圆	0.2	0.3	0.2	0.1	0.2
	同心双椭圆	0.1	0.3	0.3	0.2	0.1
	球面	0.2	0.3	0.2	0.2	0.1
	三角形	0.3	0.2	0.2	0.1	0.2
	无	0.25	0.25	0.25	0.25	0.25

相对运动状态	逼近	绕飞	跟飞	在轨机动	远离
逼近	0.3	0.2	0.2	0.2	0.1
绕飞	0.1	0.3	0.2	0.2	0.2
跟飞	0.2	0.2	0.3	0.1	0.2
在轨机动	0.2	0.2	0.1	0.3	0.2
远离	0	0.1	0.1	0.3	0.5

子意图	相对运动状态序列
抵近探测	$ {m}_{1}-{m}_{1}-{m}_{2} $
巡航探查	$ {m}_{1}-{m}_{4}-{m}_{1} $
近距后撤	$ {m}_{4}-{m}_{5}-{m}_{4} $
电磁干扰	$ {m}_{1}-{m}_{1}-{m}_{3} $

输入特征	特征状态	相对运动状态
输入特征	特征状态	逼近	在轨机动	远离
相对速度	慢	0.1	0.2	0.3
	中	0.1	0.7	0.4
	快	0.8	0.1	0.3
相对距离	近	0.1	0.3	0.6
	中	0.3	0.4	0.3
	远	0.6	0.3	0.1
飞行方向	正向	1	0.5	0.7
飞行方向	反向	0	0.5	0.3
轨道阶段	抵近	0.6	0.1	0
	保持	0.4	0.7	0.3
	飞离	0	0.2	0.7
编队队形	椭圆	0.2	0.1	0.2
	同心双椭圆	0.1	0.3	0.2
	球面	0.2	0.3	0.1
	三角形	0.3	0.2	0.3
	无	0.2	0.1	0.2