Scenario-Driven and Intelligent Optimization of Disposition Scheme for Air Defense

doi:10.3969/j.issn.1009-086x.2023.03.001

Abstract

Abstract:

Aiming at the complex battlefield situation and diversified weapons and equipments in the modern battlefield， a typical air defense scene model is constructed. Mathematical model and the program， and the pre-optimization design scheme of the defense resources deployment under multiple constraints are obtained by using intelligent solution algorithm. Optimization design and solution are carried out in typical scenarios by using the nested genetic algorithm for the coverage issues of the detecting perceptual resources, and the intercepting and striking resources. The results show that the nested optimization algorithm can optimize the deployment of operational elements of air defense in typical scenes in a short time. Compared with traditional experience-based methods， the resource deployment scheme given by the optimization design has a higher value of space coverage ratio.

Key words: air defense operation, resources deployment, nested genetic algorithm, space coverage ratio

摘要：

针对现代化战争复杂的战场态势和多样化的武器装备，构建了典型的防空场景模型并将其数学化和程序化，采用智能求解算法获得了多约束条件下防御资源部署的优化设计方案。采用多层嵌套遗传算法，针对典型场景下的探测感知资源和拦截打击资源的空间覆盖问题进行了优化求解。研究结果表明采用智能优化算法可以在相对较短的时间内对典型场景的防空作战要素部署方案进行优化设计。与基于经验的方法对比，优化后的部署方案具有更高的空间覆盖率。

关键词: 防空作战, 资源部署, 嵌套遗传算法, 空间覆盖率

CLC Number:

Mingnan TANG, Chenglong ZHANG, Qiang ZHAO, Linlin LI. Scenario-Driven and Intelligent Optimization of Disposition Scheme for Air Defense[J]. Modern Defense Technology, 2023, 51(3): 1-9.

唐明南, 张承龙, 赵强, 李林林. 任务场景驱动的防空资源部署方案智能生成与优化方法[J]. 现代防御技术, 2023, 51(3): 1-9.

Figures/Tables 12

Fig. 1 Schematic diagram of optimized disposition scheme for detecting perceptual resources

Fig. 2 Schematic diagram of optimized disposition scheme for intercepting and striking resources

Fig. 3 Schematic diagram of joint deployment scheme of two types of resources

Fig. 4 Schematic diagram of optimized disposition scheme for different interception directions （west attack as an example）

Fig. 5 Diagram of intelligent generation of resources deployment plan for air defense

Fig. 6 Flowchart of nested genetic algorithm

Table 1 Values of optimization function of intercepting and striking resources

计算代数	嵌套遗传算法	遍历法
500	0.42	0.31
2000	0.44	0.31
10⁴	—	0.35
5×10⁴	—	0.37
10⁵	—	0.38
2×10⁵	—	0.38

Fig. 7 Thermal diagram of the number of detecting perceptual resources covering random sampling points

Fig. 8 Thermal diagram of the number of intercepting and striking resources covering random sampling points

Fig. 9 Sequence diagram of actual effect of detecting perceptual resources

Fig. 10 Sequence diagram of actual effect of intercepting and striking resources

Fig. 11 Intercepting and striking resources deployment at 30° discrete angle for the unknown attacking direction

References 10

1	付强，王刚，范成礼，等. 防空反导智能指控系统作战需求研究［J］. 火力与指挥控制， 2020， 45（2）： 28-31.
	FU Qiang， WANG Gang， FAN Chengli， et al. Research on Combat Demand of Air Defense Anti-Missile Intelligent Command and Control System［J］. Fire Control & Command Control， 2020， 45（2）： 28-31.
2	姚保寅，毛磊，王智斌. 人工智能技术在航天装备领域应用探讨［J］. 现代防御技术， 2023， 51（2）： 33-42.
	YAO Baoyin， MAO Lei， WANG Zhibin. Applications of Artificial Intelligence in Space Equipment［J］. Modern Defence Technology， 2023， 51（2）： 33-42.
3	岳松堂，徐洪群，吴晓鸥，等. 美陆军一体化防空反导作战指挥系统发展研究［J］. 火力与指挥控制， 2019， 44（11）： 1-3， 10.
	YUE Songtang， XU Hongqun， WU Xiaoou， et al. Development Summing up of Integrated Air and Missile Defense Battle Command System of US Army［J］. Fire Control & Command Control， 2019， 44（11）： 1-3， 10.
4	王超，赵晓哲，康晓予. 面向编队协同防空决策的多智能体规划方法［J］. 舰船电子工程， 2009， 29（1）： 62-64.
	WANG Chao， ZHAO Xiaozhe， KANG Xiaoyu. A Multi-agent Planning Method Oriented Formation Cooperative Anti-air Decision［J］. Ship Electronic Engineering， 2009， 29（1）： 62-64.
5	季军亮，李龙跃，杨小雷，等. 改进匈牙利法的多层反导协同作战目标分配模型［J］. 现代防御技术， 2022， 50（5）： 59-67.
	JI Junliang， LI Longyue， YANG Xiaolei， et al. Targets Allocation Model of Muti-layer Anti-missile Cooperative Operation Based on Improved Hungarian Algorithm［J］. Modern Defence Technology， 2022， 50（5）： 59-67.
6	张自立，武卫东. 防空智能火力分配的实现方法［J］. 火力与指挥控制， 2006， 31（2）： 75-77.
	ZHANG Zili， WU Weidong. Method of Aptitudinally Distributing Firepower in Aerial Defence［J］. Fire Control and Command Control， 2006， 31（2）： 75-77.
7	刘泽宇，董晨，师鹏，等. 防空体系作战能力评估方法［J］. 火力与指挥控制， 2019， 44（11）： 35-40.
	LIU Zeyu， DONG Chen， SHI Peng， et al. Research on Evaluation Method of Air Defense System-of-System Combat Capability［J］. Fire Control & Command Control， 2019， 44（11）： 35-40.
8	张蛟，王中许，陈黎，等. 具有多次拦截时机的防空火力分配建模及其优化方法研究［J］. 兵工学报， 2014， 35（10）： 1644-1650.
	ZHANG Jiao， WANG Zhongxu， CHEN Li， et al. Modeling and Optimization on Antiaircraft Weapon-Target Assignment at Multiple Interception Opportunity［J］. Acta Armamentarii， 2014， 35（10）： 1644-1650.
9	阎炼，宋海凌. 改进粒子群算法的防空导弹目标分配方法研究［J］. 现代防御技术， 2019， 47（2）： 48-54， 153.
	YAN Lian， SONG Hailing. Target Assignment Method of Air Defence Missile Based on Improved Particle Swarm Optimization［J］. Modern Defence Technology， 2019， 47（2）： 48-54， 153.
10	张昀普，单甘霖，付强. 多传感器协同地面目标跟踪的调度方法［J］. 西安电子科技大学学报， 2022， 49（5）： 100-108.
	ZHANG Yunpu， SHAN Ganlin， FU Qiang. Scheduling Method for Multi-sensor Cooperative Ground Target Tracking［J］. Journal of Xidian University， 2022， 49（5）： 100-108.