基于知识引导遗传算法的防空资源分配及重构方法

doi:10.16182/j.issn1004731x.joss.26-0479

摘要/Abstract

摘要：

针对防空体系作战资源智能分配及重构过程中传统求解方法难以满足实时性要求的问题，立足于拦截时序-传感器-武器-目标的动态分配与重构问题的智能求解方法，建立了以毁伤效能和作战成本为优化对象的多约束模型，提出一种基于知识引导遗传优化算法（knowledge-guided genetic optimization method， KGGOM）的求解方法。通过知识引导种群的生成和进化，约束感知算子及修正机制、多路径搜索结合模拟退火机制对基因进行修正，提高算法的寻优能力和速度。引入历史优良方案保留机制和动态精英保留机制，以实现作战资源的快速重构。仿真结果表明：与GA和PSO相比，KGGOM在资源分配中的优化性能提升了4%~5%，重构时提升了14%，资源分配及重构时的平均收敛时间减少约70%~80%，且解的稳定性更优，为防空资源的动态分配与重构提供了一种高效求解方法。

关键词: 分配与重构, 知识引导遗传优化, 约束感知, 多路径搜索, 动态精英, 防空资源

Abstract:

To address the challenge that traditional solving methods cannot meet real-time requirements in the intelligent allocation and reconstruction of air defense operation resources, this paper focuses on an intelligent solving method for the dynamic allocation and reconstruction of intercept timing sensor-weapon-target. A multi-constraint model is established with damage effectiveness and operation cost as optimization objectives, and a knowledge-guided genetic optimization method (KGGOM) is proposed. Through knowledge-guided population generation and evolution, constraint-aware operators with correction mechanisms, and multi-path search combined with simulated annealing for gene correction, it improves its optimization capability and speed. Historical superior solution retention and dynamic elite retention mechanisms are introduced to achieve rapid reconstruction of operation resources. Simulation results demonstrate that, compared with traditional genetic algorithm (GA) and particle swarm optimization (PSO), KGGOM improves optimization performance by 4%-5% in resource allocation and by 14% in reconstruction, reduces the average convergence time by about 70%-80% during resource allocation and reconstruction, and has solutions with better stability. This study provides an efficient solving method for the dynamic allocation and reconstruction of air defense resources.

Key words: allocation and reconstruction, knowledge-guided genetic optimization method (KGGOM), constraint-aware, multi-path search, dynamic elite, air defense resource

中图分类号:

TP391.9

陈教雄,张承龙,赵玉强等 . 基于知识引导遗传算法的防空资源分配及重构方法[J]. 系统仿真学报, 2026, 38(10): 3028-3051.

Chen Jiaoxiong,Zhang Chenglong,Zhao Yuqiang,et al . Air Defense Resource Allocation and Reconstruction Method Based on KGGOM[J]. Journal of System Simulation, 2026, 38(10): 3028-3051.

图/表 22

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

表1

图13

图14

图15

图16

表2

图17

图18

图19

图20

参考文献 27

[1]	刘世豪, 崔小舟, 王斐斐, 等. 基于混合粒子群算法的防空装备软硬杀伤目标分配方法研究[J]. 现代防御技术, 2025, 53(1): 97-107.
	Liu Shihao, Cui Xiaozhou, Wang Feifei, et al. Research of Hard and Soft Killing Weapon Target Assignment Based on Hybrid Particle Swarm Optimization[J]. Modern Defence Technology, 2025, 53(1): 97-107.
[2]	章露露, 赵晨羽, 蔡云泽, 等. 基于新初始化策略的任务分配方法[J]. 航空科学技术, 2026, 37(6): 99-106.
	Zhang Lulu, Zhao Chenyu, Cai Yunze, et al. A New Initialization Strategy for Task Assignment Problem[J]. Aeronautical Science & Technology, 2026, 37(6): 99-106.
[3]	Manne A S. A Target-assignment Problem[J]. Operations Research, 1958, 6(3): 346-351.
[4]	周玉虎, 王桐, 陈立伟, 等. 基于人工蜂群算法的大规模武器目标分配研究[J]. 哈尔滨工程大学学报, 2024, 45(6): 1187-1195.
	Zhou Yuhu, Wang Tong, Chen Liwei, et al. Large-scale Weapon-target Allocation Based on an Artificial Bee Colony Algorithm[J]. Journal of Harbin Engineering University, 2024, 45(6): 1187-1195.
[5]	Davis M T, Robbins M J, Lunday B J. Approximate Dynamic Programming for Missile Defense Interceptor Fire Control[J]. European Journal of Operational Research, 2017, 259(3): 873-886.
[6]	Lu Yiping, Chen D Z. A New Exact Algorithm for the Weapon-target Assignment Problem[J]. Omega, 2021, 98: 102138.
[7]	Mehmet Fatih Hocaoğlu. Weapon Target Assignment Optimization for Land Based Multi-air Defense Systems: A Goal Programming Approach[J]. Computers & Industrial Engineering, 2019, 128: 681-689.
[8]	Kim Yeonseung, Cho Jaeyoung, Han Sangwoo, et al. Weapon Target Assignment Model for Small Unit Ground Combat Using Mixed Integer Nonlinear Program and Lagrangian Relaxation[J]. Mathematical Problems in Engineering, 2022, 2022(1): 9228993.
[9]	Sun Ying, Chen Jiangao, Cao Jiajun. Research on Weapon Target Assignment of Anti-tank Missile Based on DE Algorithm[C]//2025 Joint International Conference on Automation-Intelligence-Safety (ICAIS) & International Symposium on Autonomous Systems (ISAS). Piscataway: IEEE, 2025: 1-5.
[10]	隆雨佟, 陈爱国, 史红权, 等. 基于改进差分进化算法的跨平台武器目标分配方法[J]. 系统工程与电子技术, 2024, 46(3): 953-962.
	Long Yutong, Chen Aiguo, Shi Hongquan, et al. Cross Platform Weapontarget Allocation Method Based on Improved Differential Evolution Algorithm[J]. Systems Engineering and Electronics, 2024, 46(3): 953-962.
[11]	陈阳, 李姜, 王烨, 等. 基于改进灰狼算法求解武器目标分配问题[J]. 兵器装备工程学报, 2025, 46(6): 227-233.
	Chen Yang, Li Jiang, Wang Ye, et al. Solving Weapon Target Assignment Problem Based on Modified Gray Wolf Algorithm[J]. Journal of Ordnance Equipment Engineering, 2025, 46(6): 227-233.
[12]	陈旭祎, 马铭希, 谢海峰, 等. 基于改进鲸鱼优化算法求解的动态武器目标分配问题[J]. 兵器装备工程学报, 2026, 47(4): 16-26.
	Chen Xuyi, Ma Mingxi, Xie Haifeng, et al. Research on Improved Whale Optimization Algorithm for Solving Dynamic Weapon Target Assignment Problem[J]. Journal of Ordnance Equipment Engineering, 2026, 47(4): 16-26.
[13]	宰光军, 徐旺旺, 钟李红, 等. 基于自适应禁忌搜索多目标鲸鱼算法的武器目标分配[J]. 郑州大学学报(理学版), 2026, 58(2): 55-63.
	Zai Guangjun, Xu Wangwang, Zhong Lihong, et al. Weapon Target Assignment Based on Adaptive Tabu Search Multi-objective Whale Optimization Algorithm[J]. Journal of Zhengzhou University(Natural Science Edition), 2026, 58(2): 55-63.
[14]	陆志沣, 汪达旺, 邱子彰, 等. 基于粒子群优化和大规模邻域搜索算法的导弹火力资源调度方法[J]. 系统仿真技术, 2024, 20(4): 371-381.
	Lu Zhifeng, Wang Dawang, Qiu Zizhang, et al. Missile Firepower Resource Scheduling Method Based on Particle Swarm Optimization and Large-scale Neighborhood Search Algorithm[J]. System Simulation Technology, 2024, 20(4): 371-381.
[15]	He Liangliang, Geng Xiutang, Zhang Peng, et al. Genetic Algorithms with Elitism-immigration Strategies for Weapon-target Assignment[C]//International Conference on Artificial Intelligence and Machine Learning Research (CAIMLR 2024). Bellingham: SPIE, 2025: 136350U.
[16]	Han Yu, Pan Wei, Huang Feng, et al. Fuzzy Adaptive Chaos Genetic Algorithm for Target Assignment System[C]//2025 37th Chinese Control and Decision Conference (CCDC). Piscataway: IEEE, 2025: 4518-4523.
[17]	Niu Qianru, Ren Shuangyin, Gao Wei, et al. Modeling and Solving Weapon-target Assignment for Ship Anti-UAV Defense Using an Improved Genetic Algorithm[C]//2025 IEEE International Conference on Unmanned Systems (ICUS). Piscataway: IEEE, 2025: 392-398.
[18]	Wang Haoran, Wang Qing, Xin Bin, et al. Optimization of Multi-platform Dynamic Weapon-target Assignment Based on Multi-agent Reinforcement Learning[C]//2025 44th Chinese Control Conference (CCC). Piscataway: IEEE, 2025: 2322-2327.
[19]	Li Wenhua, Yao Xingyi, Li Kaiwen, et al. Knowledge-guided Competitive Evolutionary Algorithm for Multi-solution Sensor-weapon-target Assignment Problem[J/OL]. IEEE Transactions on Evolutionary Computation. (2026-01-13) [2026-03-10]. .
[20]	Peng Zhe, Lu Zhifeng, Mao Xiao, et al. Multi-ship Dynamic Weapon-target Assignment via Cooperative Distributional Reinforcement Learning with Dynamic Reward[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2025, 9(2): 1843-1859.
[21]	Cappart Quentin, Chételat Didier, Khalil Elias B, et al. Combinatorial Optimization and Reasoning with Graph Neural Networks[J]. Journal of Machine Learning Research, 2023, 24(130): 1-61.
[22]	Peng Yao, Guo Jia, Yang Chenyang. Learning Resource Allocation Policy: Vertex-GNN or Edge-GNN?[J]. IEEE Transactions on Machine Learning in Communications and Networking, 2024, 2: 190-209.
[23]	Ma Ziyuan, Xiong Jun, Gong Huajun, et al. Adaptive Depth Graph Neural Network-based Dynamic Task Allocation for UAV-UGVs Under Complex Environments[J]. IEEE Transactions on Intelligent Vehicles, 2025, 10(5): 3573-3586.
[24]	孙栋一, 蒲宇亭, 章建榜. 基于GA-BP神经网络的防空导弹实时目标分配方法[J]. 空天防御, 2025, 8(1): 62-70.
	Sun Dongyi, Pu Yuting, Zhang Jianbang. Target Assignment Method of Air Defense Missile Based on GA-BP Neural Network[J]. Air & Space Defense, 2025, 8(1): 62-70.
[25]	邱少明, 刘良玉, 黄昕晨, 等. 基于改进PSO-DQN的动态火力分配算法[J]. 电光与控制, 2025, 32(6): 24-30.
	Qiu Shaoming, Liu Liangyu, Huang Xinchen, et al. A Dynamic Weapon-target Assignment Algorithm Based on Improved PSO-DQN[J]. Electronics Optics & Control, 2025, 32(6): 24-30.
[26]	张腾, 王铮, 王旭阳, 等. 基于变邻域量子粒子群优化的异构反无装备群目标分配方法[J]. 弹箭与制导学报, 2026, 46(1): 61-76.
	Zhang Teng, Wang Zheng, Wang Xuyang, et al. A Target Assignment Method Based on Variable Neighborhood Quantum Particle Swarm Optimization for Heterogeneous Anti-unmanned Equipment Swarms[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2026, 46(1): 61-76.
[27]	孙苗苗, 张逊, 孟祥慈, 等. 基于分割时间窗的武器任务分配优化算法[J]. 战术导弹技术, 2023(3): 42-50, 88.
	Sun Miaomiao, Zhang Xun, Meng Xiangci, et al. Weapon Target Assignment Optimization Using the Segmented Time Window[J]. Tactical Missile Technology, 2023(3): 42-50, 88.

类型	威胁值	威胁等级	目标价值
T1	3	高	20
T2	2	中	10
T3	1	低	10
T4	1.5	低	30
T5	2.5	中	35
T6	2	中	40
T7	3	高	30
T8	2.5	中	30
T9	2	中	45
T10	2	中	25
T11	2.5	中	25
T12	1	低	30