Training Simulation Scenario Generation Based on Particle Swarm Optimization

doi:10.16182/j.issn1004731x.joss.23-0581

Abstract

Abstract:

The training effect in the training simulation scenario is not ideal. Therefore, in order to obtain the training simulation scenario with a better training effect, the training simulation scenario is optimized, and a training simulation scenario generation method based on the PSO algorithm is proposed. A fitness function is constructed based on the improved situation assessment method of the power field model, and the ability weight parameters are determined by combining the improved AHP with computer simulation software; by instantiating particles with the attributes of the combat platform, the particle swarm optimization algorithm is improved to solve the optimization scheme of training simulation scenarios. The method is validated using computer simulation cases, and the training simulation scenario results before and after optimization are compared on a computer simulation platform. The results show that this method can adjust the difficulty of training simulation scenarios, effectively help optimize the generation of training simulation scenarios, and solve the optimization generation problem of training simulation scenarios.

Key words: training simulation scenario, PSO, fitness function, power field model, AHP

CLC Number:

TP391

Gong Jianxing, Wang Zimu, Yang Qilong. Training Simulation Scenario Generation Based on Particle Swarm Optimization[J]. Journal of System Simulation, 2023, 35(9): 1860-1870.

Figures/Tables 13

Fig. 1

Table 1

Fig. 2

Table 2

Table 3

Table 4

Fig. 3

Fig. 4

Table 5

Fig. 5

Fig. 6

Fig. 7

Table 6

References 17

1	王子沐. 训练仿真想定匹配和生成方法研究[D]. 长沙: 国防科技大学, 2022.
2	杨秀霞, 罗超, 张毅. 基于威力场的导弹队形选择方法[J]. 兵器装备工程学报, 2019, 40(2): 15-18.
	Yang Xiuxia, Luo Chao, Zhang Yi. Method of Missile Formation Selection Based on Combat Power Field[J]. Journal of Ordnance Equipment Engineering, 2019, 40(2): 15-18.
3	王永攀, 苏建新, 龚明, 等. 面向作战的雷达全功能操作训练效果评估模型[J]. 系统工程与电子技术, 2022, 44(12): 3766-3774.
	Wang Yongpan, Su Jianxin, Gong Ming, et al. Combat-oriented Effect Evaluation Model of Full Function Operation Training of Radar[J]. Systems Engineering and Electronics, 2022, 44(12): 3766-3774.
4	张最良. 军事运筹学[M]. 北京: 军事科学出版社, 1997.
5	姜雪洁, 房立金. 基于模拟退火算法的机械臂刚度辨识构型优化与实验[J]. 农业机械学报, 2023, 54(1): 419-424.
	Jiang Xuejie, Fang Lijin. Method and Experiment of Configuration Optimization for Manipulator Stiffness Identification Based on Simulated Annealing Algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(1): 419-424.
6	季顺松, 黄炎焱, 张寒, 等. 基于改进遗传算法的火力分配寻优模型研究[J]. 南京理工大学学报, 2023, 47(1): 33-40.
	Ji Shunsong, Huang Yanyan, Zhang Han, et al. Research on Optimization Model of Firepower Allocation Based on Improved Genetic Algorithm[J]. Journal of Nanjing University of Science and Technology, 2023, 47(1): 33-40.
7	杨山亮, 黄健, 刘洋, 等. 基于遗传算法的联合火力WTA问题研究[J]. 计算机仿真, 2012, 29(3): 61-63, 136.
	Yang Shanliang, Huang Jian, Liu Yang, et al. Analysis of Weapon Target Assignment Problem in Joint Fire Strike Solving by Genetic Algorithm[J]. Computer Simulation, 2012, 29(3): 61-63, 136.
8	冯茜, 李擎, 全威, 等. 多目标粒子群优化算法研究综述[J]. 工程科学学报, 2021, 43(6): 745-753.
	Feng Qian, Li Qing, Quan Wei, et al. Overview of Multiobjective Particle Swarm Optimization Algorithm[J]. Chinese Journal of Engineering, 2021, 43(6): 745-753.
9	陈帅, 王勇, 吕丰, 等. 基于粒子群BP神经网络的短期电力负荷预测[J]. 上海电力学院学报, 2014, 30(2): 131-135.
	Chen Shuai, Wang Yong, Feng Lü, et al. Short-term Load Forecasting Based on the Particle Swarm BP Neural Network[J]. Journal of Shanghai University of Electric Power, 2014, 30(2): 131-135.
10	胡一波. 求解约束优化问题的几种智能算法[D]. 西安: 西安电子科技大学, 2009.
	Hu Yibo. Several Intelligent Algorithms for Constrained Optimization Problems[D]. Xi'an: Xidian University, 2009.
11	武健, 舒健生, 赵建波. 基于场论的巡航导弹作战威胁建模[J]. 四川兵工学报, 2009, 30(9): 50-52.
12	Stam J. Stable Fluids[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques. USA: ACM Press/Addison-Wesley Publishing Co., 1999: 121-128.
13	Peachey D R. Modeling Waves and Surf[J]. ACM SIGGRAPH Computer Graphics, 1986, 20(4): 65-74.
14	周焘, 任波, 于雷. 基于威力场的空战分析建模[J]. 系统仿真学报, 2008, 20(3): 738-740, 745.
	Zhou Tao, Ren Bo, Yu Lei. Modeling of Air Combat Analysis Based on Combat Power Field[J]. Journal of System Simulation, 2008, 20(3): 738-740, 745.
15	常一哲, 李战武, 孙源源, 等. 基于威力场的超视距协同空战态势评估方法[J]. 火力与指挥控制, 2015, 40(10): 40-45.
	Chang Yizhe, Li Zhanwu, Sun Yuanyuan, et al. Situation Assessment Method for Cooperative Air Combat Based on Combat Power Field[J]. Fire Control & Command Control, 2015, 40(10): 40-45.
16	李战武, 常一哲, 杨海燕, 等. 基于动态威力场的协同空战态势评估方法研究[J]. 系统仿真学报, 2015, 27(7): 1584-1590.
	Li Zhanwu, Chang Yizhe, Yang Haiyan, et al. Situation Assessment Method for Cooperative Air Combat Based on Dynamic Combat Power Field[J]. Journal of System Simulation, 2015, 27(7): 1584-1590.
17	许龙, 邵太华, 陈洪辉. 基于蒙特卡洛仿真的营打击点阵参数预测方法[J]. 火力与指挥控制, 2022, 47(10): 87-91.
	Xu Long, Shao Taihua, Chen Honghui. Prediction Method of Batting Lattice Parameters Based on Monte Carlo Simulation[J]. Fire Control & Command Control, 2022, 47(10): 87-91.

能力a和b仿真胜率差值/%	能力a相对于b 重要性标度	能力a相对于b的重要性
[0~20]	1	相同
(20~30]	2	稍小重要
(30~40]	3	稍微重要
(40~50]	4	更为重要
(50~60]	5	明显重要
(60~70]	6	十分重要
(70~80]	7	强烈重要
(80~90]	8	更强烈重要
(90~100]	9	极端重要

能力	攻击能力	探测能力	干扰能力	通信能力
攻击能力	1.000	2.000	3.000	4.000
探测能力	0.500	1.000	2.000	3.000
干扰能力	0.333	0.500	1.000	2.000
通信能力	0.250	0.333	0.500	1.000

能力系数因子	特征向量	权重值/%	最大特征值	CI
攻击能力	1.864	46.583	4.032	0.010
探测能力	1.108	27.714
干扰能力	0.645	16.106
通信能力	0.385	9.596

战机	被射击数	被击落数
r1	16	11
r2	149	100
r3	152	98

战机	被射击数	被击落数
r1	77	53
r2	112	61
r3	121	68