基于AGE-MOEA的杀伤链建模与优化方法

doi:10.12382/bgxb.2023.0566

摘要/Abstract

摘要：

针对武器装备体系的杀伤链设计问题,提出一种基于自适应几何估计多目标进化算法(Adaptive Geometry Estimation based Multi-Objective Evolutionary Algorithm, AGE-MOEA)的杀伤链建模与优化方法。围绕杀伤链闭合的设计思路,结合OODA循环理论,以传统火力分配模型为基础,综合考虑侦察、指控、打击3类武器装备,建立以打击效能最大、武器消耗最小和损毁威胁最小为目标函数,以装备使用约束、杀伤链关系约束和毁伤门限约束为约束条件的杀伤链设计多目标优化数学模型,实现对杀伤链设计问题数学表征;提出基于AGE-MOEA的杀伤链优化设计方法流程,用于求解杀伤链设计多目标优化数学模型。进行数值仿真实验和防空反导作战场景下的杀伤链设计实验。研究结果表明:杀伤链建模与优化方法能够保证所有目标杀伤链闭合的前提下,同时追求打击效能、武器消耗和损毁威胁最优,求解得到杀伤链方案,形成分布式杀伤力;验证了杀伤链设计多目标优化数学模型的科学性,AGE-MOEA求解杀伤链设计问题的有效性,以及杀伤链设计方法在实际军事作战问题的可行性。

关键词: 杀伤链, 杀伤网, OODA循环, 多目标优化

Abstract:

A modeling and optimization method of kill chains based on adaptive geometry estimation-based multi-objective evolutionary algorithm (AGE-MOEA ) is proposed for the kill-chains design. Based on the idea of kill chain closure, the OODA cycle theory and the traditional weapon target assignment model, a multi-objective optimization mathematical model of kill chains design is constructed to realize the mathematical representation of kill chains design problem. The proposed model comprehensively considers three kinds of equipment, which are used for reconnaissance, command and attack, respectively, and takes the maximum attack efficiency, minimum weapon consumption and minimum damage threat as the objective functions, and takes the equipment use constraints, kill chain relation constraints and damage threshold constraints as constraint conditions. The algorithm flow of kill chains optimization design based on AGE-MOEA is proposed to solve the multi-objective optimization mathematical model of kill chains design. Through the numerical experiments and the kill chain design experiments in air defense and anti-missile combat scenarios, the results show that the proposed method can simultaneously pursue the optimization of attack efficiency, weapon consumption and damage threat on the premise of ensuring that all kill chains of each target are closed, and obtain a kill chain solution, which can form a distributed lethality. The scientificity of multi-objective optimization mathematical model of kill chains design, the effectiveness of AGE-MOEA algorithm in solving kill chains design problems and the feasibility of kill chain design method in practical military operations are verified.

Key words: kill chain, kill web, OODA loop, multi-objective optimization

中图分类号:

E917

万斯来, 王国新, 明振军, 李传浩, 阎艳, 丁伟, 袁珂, 王玉茜. 基于AGE-MOEA的杀伤链建模与优化方法[J]. 兵工学报, 2024, 45(8): 2617-2628.

WAN Silai, WANG Guoxin, MING Zhenjun, LI Chuanhao, YAN Yan, DING Wei, YUAN Ke, WANG Yuqian. Modeling and Optimization Method of Kill Chains Based on AGE-MOEA[J]. Acta Armamentarii, 2024, 45(8): 2617-2628.

图/表 13

参考文献 33

[1]	罗鹏程, 傅攀峰, 周经伦. 武器装备体系作战能力评估框架[J]. 系统工程与电子技术, 2005, 27(1): 72-75.
	LUO P C, FU P F, ZHOU J L. Combat capability evaluation framework of weapon system of system[J]. Systems Engineering and Electronics, 2005, 27(1): 72-75. (in Chinese)
[2]	陈启宏, 赵青松, 邱薇, 等. 基于动态博弈的武器装备体系发展规划论证方法[J]. 系统工程与电子技术, 2022, 44(10): 3124-3133. doi: 10.12305/j.issn.1001-506X.2022.10.16
	CHEN Q H, ZHAO Q S, QU W, et al. Planning and demonstration method of weapon system of system based on dynamic game[J]. Systems Engineering and Electronics, 2022, 44(10): 3124-3133. (in Chinese)
[3]	SHIH C, KOONG C, HSIUNG P. Billiard combat modeling and simulation based on optimal cue placement control and strategic planning[J]. Journal of Intelligent & Robotic Systems, 2012, 67(1): 25-41.
[4]	SMITH R M. Using kill-chain analysis to develop surface ship CONOPs to defend against anti-ship cruise missiles[D]. Monterey, CA, US: Naval Postgraduate School, 2010.
[5]	陈登, 陈楚湘, 周春华. 基于“OODA环”的杀伤网节点重要性评估[J]. 兵工学报, 2024, 45(2): 363-372. doi: 10.12382/bgxb.2022.0623
	CHEN D, CHEN C X, ZHOU C H. Importance evaluation of kill web nodes based on OODA Ring[J]. Acta Armamentarii, 2024, 45(2): 363-372. (in Chinese) doi: 10.12382/bgxb.2022.0623
[6]	高保慧, 胡海. 天空海一体对海打击动态杀伤网作战概念研究[J]. 舰船电子工程, 2023, 43(1): 28-31.
	GAO B H, HU H. Research on the operational concept of sky and sea to sea strike dynamic kill web[J]. Ship Electronic Engineering, 2023, 43(1): 28-31. (in Chinese)
[7]	王玉茜, 曹亚杰, 佘晓琼, 等. 美军杀伤网概念研究及对我防空作战装备体系的启示[J]. 现代防御技术, 2023, 51(6): 1-8. doi: 10.3969/j.issn.1009-086x.2023.06.001
	WANG Y Q, CAO Y J, SHE X Q, et al. Research on the concept of kill-web of American army and its enlightenment to our air defense combat equipment system[J]. Modern Defence Technology, 2023, 51(6):1-8. (in Chinese)
[8]	王梦, 杨松, 李小波, 等. 基于可执行架构的杀伤链设计与分析优化方法[J]. 系统仿真技术, 2021, 17(3): 169-174.
	WANG M, YANG S, LI X B, et al. Kill chain design and analysis optimization method based on executable architecture[J]. System Simulation Technology, 2021, 17(3): 169-174. (in Chinese)
[9]	刘畅, 张雪松. 基于立体网络模型的机群杀伤链架构与规划研究[J]. 中国电子科学研究院学报, 2021, 16(5): 468-479.
	LIU C, ZHANG X S. Research on architecture and planning of aircraft group kill chain based on stereoscopic network model[J]. Journal of China Academy of Electronics and Information Technology, 2021, 16(5): 468-479. (in Chinese)
[10]	向南, 豆亚杰, 姜江, 等. 马赛克战概念下作战模块应急重构自主决策[J]. 指挥与控制学报, 2020, 6(3): 223-228.
	XIANG N, DOU Y J, JIANG J, et al. Operational module emergency reconstruction autonomous decision based on mosaic warfare concept[J]. Journal of Command and Control, 2020, 6(3): 223-228. (in Chinese)
[11]	钱丰, 赵红. 有无人协同杀伤链引擎设计与实现[J]. 信息化研究, 2023, 49(2): 41-47.
	QIAN F, ZHAO H. Design and implementation of man-unmanned coordinated kill chain engine[J]. Informatization Research, 2023, 49(2): 41-47. (in Chinese)
[12]	杨争争, 白浩, 侯勇. 陆战场杀伤网模型与资源优化初探[J]. 火炮发射与控制学报, 2022, 43(5): 49-53.
	YANG Z Z, BAI H, HOU Y. Preliminary study on kill net model and resource optimization of land battlefields[J]. Journal of Gun Launch & Control, 2022, 43(5): 49-53. (in Chinese)
[13]	夏博远, 杨克巍, 杨志伟, 等. 基于杀伤网评估的装备组合多目标优化[J]. 系统工程与电子技术, 2021, 43(2): 399-409. doi: 10.12305/j.issn.1001-506X.2021.02.15
	XIA B Y, YANG K W, YANG Z W, et al. Multi-objective optimization of equipment combination based on kill-web evaluation[J]. Systems Engineering and Electronics, 2021, 43(2): 399-409. (in Chinese)
[14]	万斯来, 王国新, 明振军, 等. 基于知识推理的杀伤网智能设计方法[J]. 兵工学报, 2024, 45(4): 1025-1037. doi: 10.12382/bgxb.2022.1077
	WAN S L, WANG G X, MING Z J, et al. Knowledge reasoning-based intelligent design method of kill-web[J]. Acta Armamentarii, 2024, 45(4):1025-1037. (in Chinese) doi: 10.12382/bgxb.2022.1077
[15]	SHI H Q, HE B, LIANG J, et al. Modeling technology of naval formation area antiaircraft kill web based on event graph[C]//Proceedings of the 2022 9th International Conference on Dependable Systems and Their Applications. Urumqi, China: IEEE, 2022: 353-359.
[16]	WANG L Y, CHEN L B, YANG Z W, et al. A prospect-theory-based operation loop decision-making method for kill web[J]. Mathematics, 2022, 10(19): 3486.
[17]	RICHARDS C. Boyd's OODA loop[J]. Necesse, 2020, 5(1): 142-165.
[18]	智洪欣, 赵鹏, 李中, 等. 基于可射击概率约束的防空作战火力优化分配[J]. 兵工学报, 2022, 43(4): 952-959. doi: 10.12382/bgxb.2021.0177
	ZHI H X, ZHAO P, LI Z, et al. Optimal fire allocation for air defense operations based on the shot probability constraint[J]. Acta Armamentarii, 2022, 43(4): 952-959. (in Chinese)
[19]	WANG T, FU L Y, WEI Z X, et al. Unmanned ground weapon target assignment based on deep Q-learning network with an improved multi-objective artificial bee colony algorithm[J]. Engineering Applications of Artificial Intelligence, 2023, 117: 105612.
[20]	褚凯轩, 常天庆, 张雷. 基于改进人工蜂群算法的地面作战武器-目标分配[J]. 兵工学报, 2023, 44(7): 2171-2183. doi: 10.12382/bgxb.2022.0294
	CHU K X, CHANG T Q, ZHANG L. Ground combat weapon-target allocation based on improved artificial bee colony algorithm[J]. Acta Armamentarii, 2023, 44(7): 2171-2183. (in Chinese)
[21]	ZHI P F, LIANG Z Z, ZHU W L, et al. Weapon target assignment strategy for shipboard power system considering high power pulse loads integration[J]. Energy Reports, 2023, 9(S8): 32-40.
[22]	王, 赵文飞, 滕克难, 等. 不确定因素下海上要地防空动态火力分配模型[J]. 兵工学报, 2022, 43(11): 2885-2896.
	WANG Y, ZHAO W F, TENG K N, et al. Dynamic fire distribution model for air defense at key points on sea under uncertain factors[J]. Acta Armamentarii, 2022, 43(11): 2885-2896. (in Chinese)
[23]	KIM J, LEE C, YI M Y. New weapon target assignment algorithms for multiple targets using a rotational strategy and clustering approach[J]. IEEE Access, 2022, 10: 43738-43750.
[24]	聂俊峰, 陈行军, 苏琦. 基于NSGA-Ⅲ算法的集群目标来袭火力分配建模与优化[J]. 兵工学报, 2021, 42(8): 1771-1779. doi: 10.3969/j.issn.1000-1093.2021.08.022
	NIE J F, CHEN X J, SU Q. Clustering target incoming fire distribution modeling and optimization based on NSGA-Ⅲ algorithm[J]. Acta Armamentarii, 2021, 42(8): 1771-1779. (in Chinese)
[25]	PANICHELLA A. An adaptive evolutionary algorithm based on non-euclidean geometry for many-objective optimization[C]//Proceedings of the Genetic and Evolutionary Computation Conference. New York, NY, US: Association for Computing Machinery, 2019: 595-603.
[26]	DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[27]	SHARMA S, KUMAR V A. Comprehensive review on multi-objective optimization techniques: past, present and future[J]. Archives of Computational Methods in Engineering, 2022, 29(7): 5605-5633.
[28]	DEB K, JAIN H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, Part I: solving problems with box constraints[J]. IEEE Transactions on Evolutionary Computation, 2013, 18(4): 577-601.
[29]	JAIN H, DEB K. An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, Part Ⅱ: handling constraints and extending to an adaptive approach[J]. IEEE Transactions on Evolutionary Computation. 2013, 18(4): 602-622.
[30]	BLANK J, DEB K, ROY P C.Investigating the normalization procedure of NSGA-Ⅲ[C]//Evolutionary Multi-Criterion Optimization: 10th International Conference. East Lansing, MI, US: Springer, 2019: 229-240.
[31]	THOMPSON A C, THOMPSON A C. Minkowski geometry[M]. Cambridge, UK: Cambridge University Press, 1996.
[32]	FONSECA C M, PAQUETE L, LÓPEZ-IBÁNEZ M. An improved dimension-sweep algorithm for the hypervolume indicator[C]//Proceedings of 2006 IEEE international conference on evolutionary computation. Vancouver, BC, Canada: IEEE, 2006: 1157-1163.
[33]	BLANK J, DEB K. Pymoo: multi-objective optimization in python[J]. IEEE Access, 2020, 8: 89497-89509.

装备阵营	参数	取值
	装备精度	[0.8,0.9]中取随机数
	弹药成本	[100,200]中取随机数
我方	装备成本	[400,600]中取随机数
	多目标能力	侦察:2;指控:8
	通信矩阵	[0,1]中取随机数
	指控矩阵	[0,1]中取随机数
	目标价值	[600,800]中取随机数
敌方	威胁度	[0.8,0.9]中取随机数
	毁伤门限	[0.4,0.6]中取随机数

装备阵营	参数	取值
	装备精度	[0.8,0.9]中取随机数
	弹药成本	[100,200]中取随机数
我方	装备成本	[400,600]中取随机数
	多目标能力	侦察:2;指控:8
	通信矩阵	[0,1]中取随机数
	指控矩阵	[0,1]中取随机数
	目标价值	[600,800]中取随机数
敌方	威胁度	[0.8,0.9]中取随机数
	毁伤门限	[0.4,0.6]中取随机数

算法	打击效能目标	弹药消耗目标	损毁威胁目标
AGE-MOEA	11193	2655	10141
SGA-Ⅱ	11182	2709	10499
NSGA-Ⅲ	11187	2703	10165

算法	打击效能目标	弹药消耗目标	损毁威胁目标
AGE-MOEA	11193	2655	10141
SGA-Ⅱ	11182	2709	10499
NSGA-Ⅲ	11187	2703	10165

装备类型	装备编号	数量	单元编号	装备精度	弹药成本/美元	装备成本/美元	多目标能力
侦察装备	Radar_A(SAM)	2	Radar_A_1、Radar_A_2	0.92		4000	4
	Radar_B(SAM)	2	Radar_B_1、Radar_B_2	0.94		6000	6
指控装备	指控中心(SAM)	2	指控中心_1、指控中心_2	0.95		9000	8
	Missile_A(SAM)	12	Missile_A_1~Missile_A_12	0.88	300
打击装备	Missile_B(SAM)	12	Missile_B_1~Missile_B_12	0.95	500
	Missile_C(Fighter)	8	Missile_B_1~Missile_B_8	0.9	400