Effectiveness Evaluation of Heterogeneous UAV Swarms Based on a Hybrid Model

doi:10.16182/j.issn1004731x.joss.22-1294

Abstract

Abstract:

This paper presents a hybrid model based on availability dependability capability (ADC) system performance evaluation and back propagation (BP) neural network prediction to realize a rapid performance evaluation of UAV swarms and cope with the diversity of UAV swarm configuration and state and the complexity of performance calculation. By analyzing the components of swarm performance, a capability index system including the general platform capability, system-level capability, and task execution capability of UAVs is established.By using the ADC method, a swarm combat performance sample set is generated, and the BP neural network is used to construct a comprehensive combat performance evaluation model of UAV parameters and capability indexes. The evaluation model is used to evaluate the comprehensive combat performance of heterogeneous UAV swarms. The results show that the evaluation error of this model can reach less than 5%, and the evaluation time based on samples is less than three hours, which verifies the effectiveness and high efficiency of this model in the evaluation of heterogeneous UAV swarm performance. At the same time, by analyzing the influence of quantity and configuration on the comprehensive performance of UAV swarms, feasible suggestions on the configuration of heterogeneous UAV swarms are obtained.

Key words: heterogeneous UAV, swarm system, performance evaluation, availability dependability capability-back propagation (ADC-BP) neural network, hybrid model

CLC Number:

TP391.9

Lu Yuanjie, Long Shanshan, Zhao Hang, Feng Guoxu, Zhao Xiaojia. Effectiveness Evaluation of Heterogeneous UAV Swarms Based on a Hybrid Model[J]. Journal of System Simulation, 2024, 36(3): 700-712.

Figures/Tables 13

Fig. 1

Fig. 2

Table 1

Calculation model of UAV swarm capability index

指标		内涵	模型
通用平台能力 B	飞行能力B₁	飞行速度(v)、飞行高度(H)、飞行距离(D)、飞行时间(t)和载荷(W_load)受限于相应门槛值(用上标^表示)	$B 1 = β M a v v ̂ + β H m a x H m a x H ̂ m a x + β d D D ̂ + β t t t ̂ + β W l o a d W l o a d W ̂ l o a d + β H H m i n H ̂ m i n - 1$
	经济可承受能力B₂	平台价格(P)不应高于与之对抗的地空导弹价格(M)的50%	$B 2 = P / 0.5 M - 1$
	通信导航能力B₃	由抗干扰(b₁)、加密通信(b₂)、导航装置(b₃)决定。其中，b_i 由无人机所装载的通信导航技术对应的评分决定	$B 3 = ∑ i = 1 3 ω b i b i$
	生存能力B₄	平台需要具备低可探测性，与翼展(b)、机身长度(l)、雷达反射截面积(RCS)相关^[21]	$B 4 = b^b l^l R C S^R C S 0.0625$
	环境适应能力B₅	多种环境条件下的使用能力，由温度(T)，风速(v_wind)、电磁环境(E_e)的影响程度决定	$B 5 = ω T T + ω V w i n d v w i n d + ω E e E e$
系统级能力 S	返航率S₁	可回收无人机(N_recycle)的百分比	$S 1 = N r e c y c l e N × 100 %$
	作战行动能力S₂	单位时间内的出动架次，与出动架次(N_launch)和发射时间(t_launch)相关	$S 2 = N l a u n c h t l a u n c h / N l a u n c h t l a u n c h^$
	任务规划能力S₃	单位规划时间所对应的蜂群规模，与蜂群规模(N)和任务规划时间(t_plan)相关	$S 3 = N t p l a n / N t p l a n^$
	智能自主能力S₄	由智能决策(s₁)、航路规划(s₂)、协同作战(s₃)能力决定。其中，s_i 由无人机所装载的智能化技术对应的评分决定	$S 4 = ∑ i = 1 3 ω s i s i$
任务执行能力 T	侦察干扰能力T₁	与侦察探测(C_r)、压制干扰(C_j)能力相关。其中：C_r是探测距离(R)、搜索方位角(α)、发现概率(P)、雷达/红外体制衡量系数(g)，同时跟踪目标数量(m₁)，同时允许攻击目标数量(m₂)的函数^[21]；C_j是我方无人机生存架次与出动架次的比值，即无干扰时敌方对我方的目标毁伤概率( $P k 0$ )和干扰因子(λ)的函数	$T 1 = ω C r C r + ω C j C j$ $C r = R 2 4 α 360 ∘ P g (m 1 m 2) 0.05$ $C j = 1 - P k 0 (1 - λ)$
	诱饵战能力T₂	与诱骗敌方火力消耗的能力有关，是无诱骗时敌方对我方的目标毁伤概率(P_k0)和诱骗因子(λ_d)的函数	$T 2 = P k 0 (1 + λ d)$
	反辐射能力T₃	与反辐射突防能力(C_s)、毁伤能力(C_k)相关。其中：C_s由我方反辐射无人机的生存能力决定，是敌方对我方反辐射无人机杀伤概率P_k函数；C_k由无人机对目标的命中率及在命中条件下的毁伤概率来决定，是无人机弹着点实际偏离目标雷达的距离(r)，弹着点偏离目标雷达的标准偏差(δ)，以及杀伤区半径(r₀)的函数^[22]	$T 3 = ω C s C s + ω C k C k$ $C s = 1 - P k$ $C k = 1 - e x p - r 2 2 δ 2 1 - e x p - 3 r 0 r 6$
	光电察打能力T₄	与侦察探测(C_r)、毁伤能力(C_k)能力相关。其中：C_r与C_k的计算分别同前所述^[21-22]	$T 4 = ω C r C r + ω C k C k$ $C r = R 2 4 α 360 ∘ P g (m 1 m 2) 0.05$ $C k = 1 - e x p - r 2 2 δ 2 1 - e x p - 3 r 0 r 6$

Table 1

Table 2

Weight values of UAV swarm capability index

第1层	权重	第2层	权重
平台级能力B	$ω B = 0.194$	B₁	$ω B 1$ =0.246
		B₂	$ω B 2$ =0.093
		B₃	$ω B 3$ =0.163
		B₄	$ω B 4$ =0.283
		B₅	$ω B 5$ =0.215
系统级能力S	$ω S = 0.225$	S₁	$ω S 1$ =0.127
		S₂	$ω S 2$ =0.281
		S₃	$ω S 3$ =0.281
		S₄	$ω S 4$ =0.311
任务执行能力T	$ω T = 0.582$	T₁	$ω T 1$ =0.216
		T₂	$ω T 2$ =0.153
		T₃	$ω T 3$ =0.284
		T₄	$ω T 4$ =0.347

Table 2

Table 3

Fig. 3

Fig. 4

Table 4

Table 5

Fig. 5

Fig. 6

Fig. 7

Fig. 8

References 23

1	胡杰, 陈化良, 刘亮, 等. 无人机蜂群作战效能评估研究[J]. 火力与指挥控制, 2022, 47(4): 164-168.
	Hu Jie, Chen Hualiang, Liu Liang, et al. Research on Operational Effectiveness Evaluation of UAV Swarm[J]. Fire Control & Command Control, 2022, 47(4): 164-168.
2	韩月明, 方丹, 张红艳, 等. 智能无人机集群协同作战效能评估综述[J]. 飞航导弹, 2020(8): 51-56.
3	张子伟, 郭齐胜, 董志明, 等. 体系作战效能评估与优化方法综述[J]. 系统仿真学报, 2022, 34(2): 303-313.
	Zhang Ziwei, Guo Qisheng, Dong Zhiming, et al. Review of System of Systems Combat Effectiveness Evaluation and Optimization Methods[J]. Journal of System Simulation, 2022, 34(2): 303-313.
4	Hodgkinson J, Skow A, Ettinger R, et al. Relationships Between Flying Qualities, Transient Agility, and Operational Effectiveness of Fighter Aircraft[C]//15th Atmospheric Flight Mechanics Conference. Reston, VA, USA: AIAA, 1988: AIAA 1988-4329.
5	Fielding J P, Nilubol O. A Design Assessment Methodology for Combat Aircraft Operational Effectiveness[C]//2nd AIAA "Unmanned Unlimited" Conf. and Workshop & Exhibit. Reston, VA, USA: AIAA, 2003: AIAA 2003-6551.
6	Chusilp Pawat, Charubhun Weerawut, Koanantachai Pattadon. Monte Carlo Simulations of Weapon Effectiveness Using Pk Matrix and Carleton Damage Function[J]. International Journal of Applied Physics and Mathematics, 2014, 4(4): 280-285.
7	Gu Hui, Song Bifeng. Study on Effectiveness Evaluation of Weapon Systems Based on Grey Relational Analysis and TOPSIS[J]. Journal of Systems Engineering and Electronics, 2009, 20(1): 106-111.
8	陈国际, 姜长生, 吴庆宪. 战斗机对空作战效能评估[J]. 电光与控制, 2014, 21(9): 16-18, 25.
	Chen Guoji, Jiang Changsheng, Wu Qingxian. Operational Effectiveness Evaluation of Fighter Aircrafts in Air Combat[J]. Electronics Optics & Control, 2014, 21(9): 16-18, 25.
9	张永利, 孙治水, 周荣坤. 基于AHP-模糊综合评判法的有人机/无人机协同作战效能评估[J]. 舰船电子对抗, 2015, 38(6): 80-84, 92.
	Zhang Yongli, Sun Zhishui, Zhou Rongkun. Efficiency Evaluation of Manned/Unmanned Aerial Vehicles Coordinate Operation Based on AHP-fuzzy Synthetic Evaluation Method[J]. Shipboard Electronic Countermeasure, 2015, 38(6): 80-84, 92.
10	陈士涛, 张海林. 基于作战网络模型的异构无人机集群作战能力评估[J]. 军事运筹与系统工程, 2019, 33(1): 38-43.
	Chen Shitao, Zhang Hailin. Assessment of Fighting Capability of Heterogeneous Unmanned Aerial Vchicles Cluster Based on Operation Network Model[J]. Military Operations Research and Systems Engineering, 2019, 33(1): 38-43.
11	Jia Niping, Yang Zhiwei, Yang Kewei. Operational Effectiveness Evaluation of the Swarming UAVs Combat System Based on a System Dynamics Model[J]. IEEE Access, 2019, 7: 25209-25224.
12	王瑛, 史翔宇, 李超. 基于DoDAF的无人机协同作战效能评估[J]. 空军工程大学学报(自然科学版), 2020, 21(6): 66-72.
	Wang Ying, Shi Xiangyu, Li Chao. Research on Evaluation of UAV Cooperative Combat Effectiveness Based on DoDAF[J]. Journal of Air Force Engineering University(Natural Science Edition), 2020, 21(6): 66-72.
13	罗杰, 苏兵, 翟乐育. 基于BP神经网络的空中无人通信平台作战效能评估[J]. 指挥控制与仿真, 2021, 43(4): 21-25.
	Luo Jie, Su Bing, Zhai Leyu. Operational Effectiveness Evaluation of Unmanned Aerial Communication Platform Based on BP Neural Network[J]. Command Control & Simulation, 2021, 43(4): 21-25.
14	刘万祥, 滕文志, 杨玉剑, 等. 基于改进AHP和熵权法的新型雷达作战效能评估[J]. 空军预警学院学报, 2020, 34(1): 27-30.
	Liu Wanxiang, Teng Wenzhi, Yang Yujian, et al. Evaluation on Operational Efficiency of New Type Radar Based on Improved AHP and Entropy Weight Method[J]. Journal of Air Force Early Warning Academy, 2020, 34(1): 27-30.
15	栾孝丰, 温瑞. 基于UML和ADC法的舰载反舰导弹武器系统效能评估[J]. 计算机与数字工程, 2010, 38(8): 135-137, 149.
	Luan Xiaofeng, Wen Rui. Evaluation for Ship-to-ship Missile Weapon System Effectiveness Based on UML and ADC Method[J]. Computer & Digital Engineering, 2010, 38(8): 135-137, 149.
16	李元锋, 刘建平, 石成英, 等. 基于能力测试方法和探索回归分析的体系作战效能评估[J]. 系统工程与电子技术, 2014, 36(7): 1339-1345.
	Li Yuanfeng, Liu Jianping, Shi Chengying, et al. System Operational Effectiveness Evaluation Based on Capability Test Methodology and Exploratory Regression Analysis[J]. Systems Engineering and Electronics, 2014, 36(7): 1339-1345.
17	范勇, 李为民. 基于概率分析法的无人攻击机作战效能分析模型研究[J]. 现代防御技术, 2003, 31(6): 60-64.
	Fan Yong, Li Weimin. Combat Effectiveness Analysis Models Research of Unmanned Combat Aerial Vehicle Based on Probabilistic Method[J]. Modern Defence Technology, 2003, 31(6): 60-64.
18	刘帅, 寇英信, 付昭旺, 等. 基于人工神经网络的空战效能评估[J]. 电光与控制, 2010, 17(4): 26-29.
	Liu Shuai, Kou Yingxin, Fu Zhaowang, et al. Effectiveness Evaluation of Air Combat Based on Artificial Neural Network[J]. Electronics Optics & Control, 2010, 17(4): 26-29.
19	卜晓东, 张军. 基于OODA循环的反舰导弹作战效能评估研究[J]. 现代防御技术, 2021, 49(2): 13-19.
	Bu Xiaodong, Zhang Jun. Research on Operational Effectiveness Evaluation of Antiship Missile Based on OODA Cycle[J]. Modern Defence Technology, 2021, 49(2): 13-19.
20	刘强, 薛惠锋. 基于多Agent的指控系统防空作战效能评估仿真研究[J]. 微电子学与计算机, 2008, 25(2): 126-128, 132.
	Liu Qiang, Xue Huifeng. Study of Simulation and Effect Evaluation for C2 in Air-defense Operation Based on Multi-agent[J]. Microelectronics & Computer, 2008, 25(2): 126-128, 132.
21	朱宝鎏, 朱荣昌, 熊笑非. 作战飞机效能评估[M]. 2版. 北京: 航空工业出版社, 2006: 63-80.
22	周延安, 梅刚. 反辐射无人机作战效能分析[J]. 舰船电子对抗, 2007, 30(1): 42-45.
	Zhou Yanan, Mei Gang. Analysis on Operational Effectiveness of Anti-radiation UAV[J]. Shipboard Electronic Countermeasure, 2007, 30(1): 42-45.
23	陈侠, 胡乃宽. 基于APSO-BP神经网络的无人机空地作战效能评估研究[J]. 飞行力学, 2018, 36(1): 88-92.
	Chen Xia, Hu Naikuan. Research on Effectiveness Evaluation of UAV Air-to-ground Attack Based on APSO-BP Neural Network[J]. Flight Dynamics, 2018, 36(1): 88-92.

能力	第1组评估值	第2组评估值	第3组评估值
B₁	0.795 1	0.567 7	0.276 2
B₂	0.961 6	0.422 3	0.390 0
B₃	0.944 6	0.632 8	0.247 6
B₄	0.882 5	0.546 0	0.153 3
B₅	0.782 8	0.462 4	0.263 2
S₁	0.825 7	0.663 4	0.349 3
S₂	0.881 0	0.622 2	0.285 1
S₃	0.748 9	0.599 9	0.358 8
S₄	0.814 1	0.471 4	0.280 7
T₁	0.944 7	0.463 9	0.110 4
T₂	0.837 6	0.635 3	0.258 2
T₃	0.806 9	0.560 4	0.316 8
T₄	0.784 3	0.418 5	0.343 6

[1]	Wang Yinsong, Wang Kai. Performance Evaluation Method for Load Control System Considering “Two Detailed Rules” [J]. Journal of System Simulation, 2021, 33(3): 710-720.
[2]	Liu Haozhe, Li Wei, Ma Ping, Yang Ming. System Performance Evaluation Method Based on Multi-source Prior Data [J]. Journal of System Simulation, 2021, 33(11): 2673-2680.
[3]	Sun Yifei, Cai Liangliang, Zhou Yi, Zhou Zhong. MRMark: A Machine Performance Evaluation Method for Three-dimensional Video Fusion [J]. Journal of System Simulation, 2020, 32(7): 1375-1384.
[4]	Tianyu Huang, Yunying Guo. Research of Nonlinear Time Series Prediction Method for Motion Capture [J]. Journal of System Simulation, 2018, 30(7): 2808-2815.
[5]	Yang Kun, Ge Xiangyu, Ju Pengfei, Bai Jie. Evaluation on Pilot Performance of Detecting Runway Incursion Based on Visual Simulation [J]. Journal of System Simulation, 2018, 30(5): 1967-1973.
[6]	Wang Yuxiao, Wang Songyan, Chao Tao, Yang Ming. Multi Criterion Variable Weight Comprehensive Evaluation Method of Guidance and Control System [J]. Journal of System Simulation, 2018, 30(2): 435-442.
[7]	Zhang Jianchun, Zeng Yanyang, Xu Wenpeng, Kang Fengju. Improved Hybrid DEVS-based Equipment Modeling Method [J]. Journal of System Simulation, 2018, 30(11): 4123-4131.
[8]	Liu Yi, Wang Gangqiao, Wu Zhipeng, Fan Zhenqiang, Chen Yongqiang. Scenario Computing for Analysis of Deep Uncertainty Systems [J]. Journal of System Simulation, 2018, 30(10): 3608-3615.
[9]	Zu Xianghuan, Wang Yinyan, Yang Chuanlei, Du Jianwei, Wang Jialun. Research and Implementation of EGR performance Evaluation for Turbocharged Diesel Engine [J]. Journal of System Simulation, 2017, 29(12): 3075-3081.
[10]	Zhang Denghui, Chao Tao, Wang Songyan, Ma Ping. Performance Evaluation of Guidance and Control System Based on Improved Latin Hypercube [J]. Journal of System Simulation, 2017, 29(10): 2345-2352.
[11]	Ma Xiangguo, Liu Tongjuan, Wang Li, Jiang Rongfen. Performance Evaluation of Automated Warehouse Based on Markov Chain [J]. Journal of System Simulation, 2016, 28(7): 1692-1700.
[12]	Qi Zongfeng, Han Shan, Li Jianxun. Research on Radar Anti-jamming Performance Evaluation Index System Based on Rough Set Theory [J]. Journal of System Simulation, 2016, 28(2): 335-342.
[13]	Li Fan, Geng Xu, Dong Xiaojie, Hong Zehua. Application of Mutil-level Fuzzy Algorithm in IR Countermeasure Performance Integrated Evaluation [J]. Journal of System Simulation, 2015, 27(9): 2176-2180.