动态对抗场景中的打击链在线重构方法

doi:10.12305/j.issn.1001-506X.2026.06.19

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (6): 1980-1990.doi: 10.12305/j.issn.1001-506X.2026.06.19

动态对抗场景中的打击链在线重构方法

薛羽阳¹^,²^,³(), 王涛¹^,²^,³^,*, 廖馨⁴, 许元男⁴, 林鸣昊¹^,²^,³, 吴安琪¹^,²^,³

1. 中山大学智能工程学院，广东深圳 517108
2. 广东省南方海洋科学与工程实验室，广东珠海 519000
3. 中山大学人工智能研究院群体智能研究中心，广东广州 510275
4. 中国运载火箭技术研究院研究发展中心，北京 100076

收稿日期:2025-08-18 修回日期:2025-11-04 接受日期:2025-12-16 出版日期:2026-06-25 发布日期:2026-03-20
通讯作者: 王涛 E-mail:xueyy7@mail2.sysu.edu.cn
作者简介:薛羽阳（1995—），男，博士研究生，主要研究方向为无人系统认知、无人系统控制
廖　馨（1980—），女，高级工程师，博士，主要研究方向为智能武器、作战体系
许元男（1983—），男，高级工程师，博士，主要研究方向为武器系统设计、无人系统总体设计
林鸣昊（2000—），男，硕士研究生，主要研究方向为复杂系统
吴安琪（2002—），女，硕士研究生，主要研究方向为多模态大模型

Online reconstruction method for strike chain in dynamic confrontation scenarios

Yuyang XUE¹^,²^,³(), Tao WANG¹^,²^,³^,*, Xin LIAO⁴, Yuannan XU⁴, Minghao LIN¹^,²^,³, Anqi WU¹^,²^,³

1. School of Intelligent Systems Engineering，Sun Yat-sen University，Shenzhen 517108，China
2. Southern Marine Science and Engineering Guangdong Laboratory，Zhuhai 519000，China
3. Center for Swarm Intelligence，Institute of Artificial Intelligence，Sun Yat-sen University，Guangzhou 510275，China
4. Research and Development Center，China Academy of Launch Vehicle Technology，Beijing 100076，China

Received:2025-08-18 Revised:2025-11-04 Accepted:2025-12-16 Online:2026-06-25 Published:2026-03-20
Contact: Tao WANG E-mail:xueyy7@mail2.sysu.edu.cn

摘要/Abstract

摘要：

针对动态对抗场景中因节点损毁导致打击链中断的问题，提出一种基于断点复用与局部搜索的在线重构方法。构建“物理-功能-状态”三层抽象网络模型，实现节点、连边与语义约束的统一建模。引入改进的非支配排序遗传算法（non-dominated sorting genetic algorithm, NSGA）-II以保留可用前段链路、压缩搜索空间，并结合逼近理想解的排序法（technique for order preference by similarity to ideal solution, TOPSIS）实现毫秒级的帕累托最优解决策。仿真结果表明，所提方法在链路重构时延上较传统策略降低62%，在装备资源下降20%的条件下仍可保持极高的任务完成率，且算法复杂度随节点规模线性增长，满足主流分布式作战体系对实时性与扩展性的需求。

关键词: 动态对抗, 打击链, 在线重构, 多目标优化, 非支配排序遗传算法, 逼近理想解的排序法

Abstract:

To address the problem of strike chain interruption caused by node damage in dynamic confrontation scenarios, an online reconstruction method based on breakpoint reuse and local search is proposed. A three-layer “physical–functional–state” abstract network model is constructed to achieve unified modeling of nodes, links, and semantic constraints. An improved non-dominated sorting genetic algorithm （NSGA）-II is introduced to retain usable front-end links and compress the search space, and the technique for order preference by similarity to ideal solution （TOPSIS） is combined to enable millisecond-level Pareto-optimal decision-making. Simulation results show that the proposed method reduces link reconstruction latency by 62% compared with traditional strategies, and maintains a very high mission completion rate even when equipment resources are reduced by 20%. Moreover, the algorithm complexity increases linearly with node scale, meeting the real-time and scalability requirements of mainstream distributed combat systems.

Key words: dynamic confrontation, strike chain, online reconstruction, multi-objective optimization, non-dominated sorting genetic algorithm (NSGA)-II, technique for order preference by similarity to ideal solution (TOPSIS)

中图分类号:

TP 301.6

薛羽阳, 王涛, 廖馨, 许元男, 林鸣昊, 吴安琪. 动态对抗场景中的打击链在线重构方法[J]. 系统工程与电子技术, 2026, 48(6): 1980-1990.

Yuyang XUE, Tao WANG, Xin LIAO, Yuannan XU, Minghao LIN, Anqi WU. Online reconstruction method for strike chain in dynamic confrontation scenarios[J]. Systems Engineering and Electronics, 2026, 48(6): 1980-1990.

图/表 20

图1

图2

图3

图4

图5

表1

图6

表2

表3

表4

表5

表6

图7

图8

表7

图9

表8

表9

图10

图11

参考文献 31

1	ZHANG J L, HAN K, ZHANG P, et al. A survey on joint-operation application for unmanned swarm formations under a complex confrontation environment[J]. Journal of Systems Engineering and Electronics, 2023, 34 (6): 1432- 1446. doi: 10.23919/JSEE.2023.000162
2	JIA Z Y, YOU J H, DONG C, et al. Cooperative cognitive dynamic system in UAV swarms: reconfigurable mechanism and framework[J]. IEEE Vehicular Technology Magazine, 2024, 19 (3): 90- 101. doi: 10.1109/MVT.2024.3404391
3	CHEN H, DOU Y J, CHEN Z Y, et al. A hybrid genetic algorithm to the program optimization model based on a heterogeneous network[J]. Journal of Systems Engineering and Electronics, 2025, 36 (4): 994- 1005. doi: 10.23919/JSEE.2025.000063
4	DESTA H, DANDA B R. Neuro-symbolic AI for military applications[J]. IEEE Trans. on Artificial Intelligence, 2024, 5 (12): 6012- 6026. doi: 10.1109/TAI.2024.3444746
5	WANG Y, TAO J Y, ZHANG X K, et al. Mission-oriented capability evaluation for combat network based on operation loops[J]. Defence Technology, 2024, 42, 156- 175. doi: 10.1016/j.dt.2024.07.002
6	GUO J H, ZHANG J D, WANG Z H, et al. Formation cooperative intelligent tactical decision making based on Bayesian network model[J]. Drones, 2024, 8 (9): 427. doi: 10.3390/drones8090427
7	CHEN Z W, ZHOU Z M, ZHANG L G, et al. Mission reliability modeling and evaluation for reconfigurable unmanned weapon system-of-systems based on effective operation loop[J]. Journal of Systems Engineering and Electronics, 2023, 34 (3): 588- 597. doi: 10.23919/JSEE.2023.000082
8	XU R J, LIU J H, LI J C, et al. Link-centric research on the capability resilience of heterogeneous information combat networks[J]. IEEE Trans. on Network Science and Engineering, 2025, 12 (4): 2921- 2931. doi: 10.1109/TNSE.2025.3555384
9	丁冬, 何兵, 陈明, 等. 美国导弹预警系统作战效能评估指标体系设计研究[J]. 中国电子科学研究院学报, 2022, 17 (9): 883- 891.
	DING D, HE B, CHEN M, et al. Research on design of operational effectiveness evaluation index system for american missile early warning system[J]. Journal of China Electronics Science Research Institute, 2022, 17 (9): 883- 891.
10	QI H, BO P, SEN L, et al. Evaluation method and optimization strategies of resilience for air & space defense system of systems based on kill network theory and improved self-information quantity[J]. Defence Technology, 2023, 21, 219- 239. doi: 10.1016/j.dt.2023.01.005
11	DANG Y H, WANG H X, YIN Z M, et al. Resilience analysis of coupling combat network: considering multiple destruction-recovery processes[J]. IEEE Access, 2025, 13, 100261- 100270. doi: 10.1109/ACCESS.2025.3577347
12	YE H J, GAO W. A method of kill chains fusion based on granulated rules and matrix computation[J]. IEEE Access, 2024, 12, 198224- 198236. doi: 10.1109/ACCESS.2024.3518435
13	LI B, WANG J M, SONG C, et al. Multi-UAV roundup strategy method based on deep reinforcement learning CEL-MADDPG algorithm[J]. Expert Systems with Applications, 2024, 245, 123018. doi: 10.1016/j.eswa.2023.123018
14	LI Y Y, CHEN W Y, FU B, et al. A distributed cooperative dynamic target search method for multi-UAV systems in complex adversarial environments[J]. IEEE Internet of Things Journal, 2025, 12 (18): 38155- 38171. doi: 10.1109/JIOT.2025.3585158
15	PEIYANG Z, GUODONG L. A cooperative dynamic target search approach for multi-UAV systems utilizing the MAPPO algorithm[J]. Discover Artificial Intelligence, 2025, 5, 153. doi: 10.1007/s44163-025-00411-9
16	李小波, 王蒙一, 廖咏一, 等. 智能化空天防御作战体系架构设计方法研究[J]. 现代防御技术, 2024, 52 (2): 1- 12. doi: 10.3969/j.issn.1009-086x.2024.02.001
	LI X B, WANG M Y, LIAO Y Y, et al. Research on architecture design method of intelligent air-space defense combat system[J]. Modern Defence Technology, 2024, 52 (2): 1- 12. doi: 10.3969/j.issn.1009-086x.2024.02.001
17	LYU T Q, LIU Y, WANG C, et al. Construction of an intelligent kill web operational effectiveness model considering uncertainty factors[C]//Proc. of the International Symposium on AI and Cybersecurity, 2025: 71−75.
18	ZHONG Y F, LI H X, SUN Q, et al. A kill chain optimization method for improving the resilience of unmanned combat system-of-systems [J]. Chaos, Solitons & Fractals, 2024, 181: 114685.
19	ZHANG H H, LI B, HUANG J Y, et al. A parallel multi-demonstrations generative adversarial imitation learning approach on UAV target tracking decision[J]. Chinese Journal of Electronics, 2025, 34 (4): 1185- 1198. doi: 10.23919/cje.2024.00.082
20	LIU W L, PAN Z S, HAN W, et al. Construction of kill webs with heterogeneous UAV swarms in dynamic contested environments[J]. Complex Intelligent Systems, 2025, 11, 8. doi: 10.1007/s40747-024-01644-4
21	YANG K W, XIA B Y, CHEN G, et al. Multi-objective optimization of operation loop recommendation for kill web[J]. Journal of Systems Engineering and Electronics, 2022, 33 (4): 969- 985. doi: 10.23919/JSEE.2022.000094
22	YOU Y Q, ZHANG X, HE H F, et al. Kill chain search and evaluation of weapon system of systems based on GAT-DFS[J]. Systems, 2025, 13 (8): 703. doi: 10.3390/systems13080703
23	雷洪涛, 孙立健, 朱先强, 等. 杀伤链分析构建与韧性优化方法[J]. 指挥与控制学报, 2024, 10 (6): 720- 731. doi: 10.3969/j.issn.2096-0204.2024.06.0720
	LEI H T, SUN L J, ZHU X Q, et al. Kill chain analysis construction and resilience optimization method[J]. Journal of Command and Control, 2024, 10 (6): 720- 731. doi: 10.3969/j.issn.2096-0204.2024.06.0720
24	孙利娜, 陈永禄, 陈志伟. 基于杀伤链的动态重构作战网络抗毁性分析[J]. 火力与指挥控制, 2023, 48 (2): 12- 18.
	SUN L N, CHEN Y L, CHEN Z W. Resilience analysis of dynamically reconfigured combat networks based on the kill chain[J]. Firepower & Command Control, 2023, 48 (2): 12- 18.
25	KOUR R, KARIM R, DERSIN P. Game theory and cyber kill chain: a strategic approach to cybersecurity[C]//Proc. of the International Congress and Workshop on Industrial AI and eMaintenance , 2024: 451−463.
26	KIKONG K. DAESUNG M, JUNHO H, et al. Attack graph generation with machine learning for network security[J]. Electronics, 2022, 11 (9): 1332. doi: 10.3390/electronics11091332
27	NADIA A, THIAGO V, ALI A. Integrated genetic algorithm and deep learning approach for effective cyber-attack detection and classification in industrial internet of things (IIoT) environments [J]. Arabian Journal for Science and Engineering, 2024, 49.
28	WU S Y, KANG P Q, LI J R, et al. A research on kill net generation technology of cooperative combat system based on SG-DPSO algorithm[C]//Proc. of the 4th International Conference on Autonomous Unmanned Systems , 2025: 128−138.
29	NATHAN G, W. Explainable AI in the military domain[J]. AI & Society, 2024, 26, 29.
30	LI R Z, YUAN H, REN B B, et al. Optimal unmanned combat system-of-systems reconstruction strategy with heterogeneous cost via deep reinforcement learning[J]. Mathematics, 2024, 12 (10): 1476. doi: 10.3390/math12101476
31	PENG Z, LU Z F, MAO X, et al. Multi-ship dynamic weapon-target assignment via cooperative distributional reinforcement learning with dynamic reward[J]. IEEE Trans. on Emerging Topics in Computational Intelligence, 2025, 9 (2): 1843- 1859.

名称	配置/型号
CPU	Intel i7 12700H（16 G）
显卡	NVIDIA GeForce RTX 3060（12 GB）
系统	Windows 11
软件环境	Python 3.10

名称	伪装能力	拦截能力	防护能力
航母1	0.2	0.3	0.5
航母2	0.2	0.3	0.5
驱逐舰1	0.2	0.3	0.5
驱逐舰2	0.2	0.3	0.5
轰炸机1	0.2	0.3	0.5
轰炸机2	0.2	0.3	0.5
舰载战斗机1	0.2	0.3	0.5
舰载战斗机2	0.2	0.3	0.5
补给舰	0.2	0.3	0.5

名称	探测半径/units	精度/%	扫描速率/（°/s）	雷达数量
驱逐舰1	400	99.5	12	1
驱逐舰2	800	95	12	1
预警机1	600	80	10	1
预警机2	600	80	10	1
无人机1	200	88	6	1
无人机2	200	88	6	1
无人机3	200	88	6	1
侦察机1	300	88	6	1
侦察机2	300	88	6	1
侦察机3	300	88	6	1
陆基雷达1	800	99.5	20	4
陆基雷达2	800	99.5	20	4
陆基雷达3	800	99.5	20	4
陆基雷达4	800	99.5	20	4

名称	处理速度	分析水平	分析级别
驱逐舰1	0.8	0.5	2
驱逐舰2	0.8	0.5	2
预警机1	0.3	0.6	2
预警机2	0.3	0.6	2
战役情报中心1	0.8	0.5	1
战役情报中心2	0.8	0.5	1
战术情报中心1	0.8	0.5	2
战术情报中心2	0.8	0.5	2
战术情报中心3	0.8	0.5	2
战术情报中心4	0.8	0.5	2

名称	响应系数	知识库水平	自动化程度	指挥级别
驱逐舰1	0.8	0.6	0.5	3
驱逐舰2	0.8	0.6	0.5	3
预警机1	0.85	0.7	0.4	2
预警机2	0.85	0.7	0.4	1
联合作战中心	0.85	0.7	0.4	2
战术指挥站1	0.85	0.7	0.4	2
战术指挥站2	0.85	0.7	0.4	3

动态对抗场景中的打击链在线重构方法

Online reconstruction method for strike chain in dynamic confrontation scenarios

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 20

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

名称	覆盖半径/units	弹药类型	单发成本
驱逐舰1	800	反舰、防空	1000
驱逐舰2	750	反舰、防空	500
发射车1	1000	反舰	2000
发射车2	600	反舰	2000
发射车3	1000	反舰	2000
发射车4	1000	防空	2000
发射车5	600	反舰	2000
发射车6	600	防空	2000
发射车7	600	防空	2000
发射车8	1200	防空	2000

节点类型	实际装备
侦察节点	驱逐舰1
情报分析节点	战术情报中心2
1级指挥节点	联合作战中心
2级指挥节点	预警机1
影响节点	发射车3
保障节点	仓库2
目标节点	蓝方补给舰

指标	改进NSGA-II	BF	提升率/%
f₁/ms	87±5	230±12	62
f₂	0.83±0.02	0.79±0.03	5.1
f₃/千美元	2.7±0.1	3.2±0.2	16
RT/ms	87±4	215±10	60

[1]	刘璐瑶, 金晓, 蔡金良, 张武才. 结合ANN及改进MOPSO的天线布局多目标优化[J]. 系统工程与电子技术, 2026, 48(5): 1607-1614.
[2]	谢雨思, 雷勤, 吴志彬. 考虑工作量平衡的多目标取送货路径规划[J]. 系统工程与电子技术, 2026, 48(4): 1254-1263.
[3]	朱品蝶, 吕娜. 基于时间切片的打击链通信资源动态调度算法[J]. 系统工程与电子技术, 2026, 48(4): 1441-1449.
[4]	宋祺, 黄震宇, 李寰宇, 郭安新, 杨任农. “敏捷作战运用”基地建设建模仿真研究[J]. 系统工程与电子技术, 2026, 48(1): 218-234.
[5]	李延通, 李子璠, 周姗姗, 张闯. 无人机光伏电站巡检双目标选址-路径问题研究[J]. 系统工程与电子技术, 2025, 47(8): 2612-2621.
[6]	羊钊, 胡锦标, 王艳, 齐洪彪. 考虑异巢起降的无人机山地巡检覆盖路径规划[J]. 系统工程与电子技术, 2025, 47(8): 2622-2631.
[7]	付留芳, 许林周, 周明, 董晓明, 寇祝. 基于二次优化的T-Rⁿ型多基地声纳部署方法[J]. 系统工程与电子技术, 2025, 47(5): 1600-1608.
[8]	王佩骐, 鞠儒生, 张淼, 段伟. 基于非支配遗传算法的HLA仿真系统数据采集策略[J]. 系统工程与电子技术, 2024, 46(9): 3103-3111.
[9]	洪涛, 王凡, 李治, 钟志伟, 丁晓进, 刘子威, 张更新. 业务驱动的低轨卫星物联网终端模态切换方法[J]. 系统工程与电子技术, 2024, 46(8): 2867-2876.
[10]	许强强, 柴华. 基于NSGA-Ⅱ的车载光学测量设备任务调度方案优化[J]. 系统工程与电子技术, 2024, 46(7): 2393-2400.
[11]	饶悦, 杨健, 孙国敏, 张伟, 邵怀宗, 林静然. 基于改进SA-NSGAⅡ的多波束卫星动态资源分配方法[J]. 系统工程与电子技术, 2024, 46(12): 4222-4230.
[12]	陈浩, 孙刚, 彭双, 伍江江. 基于多目标优化的测控数传资源动态重调度方法[J]. 系统工程与电子技术, 2024, 46(11): 3744-3753.
[13]	刘俊, 崔宁, 谢佳昕, 行坤. 基于NSGA-Ⅲ的机载雷达空空射频隐身探测参数设计[J]. 系统工程与电子技术, 2024, 46(1): 97-104.
[14]	高泽伦, 郑少秋, 梁汝鹏, 黄炎焱. 超网络体系作战下的打击目标优选模型[J]. 系统工程与电子技术, 2024, 46(1): 182-189.
[15]	王力尧, 张进, 周洪喜, 王柯茂. 基于物理规划的多星多站访问规划[J]. 系统工程与电子技术, 2023, 45(8): 2514-2520.