基于网络层次分析法的无人集群作战效能评估

doi:10.12305/j.issn.1001-506X.2026.10.25

摘要/Abstract

摘要：

为全面评估无人集群的作战效能，采用观察-判断-决策-行动（observe-orient-decide-act，OODA）作战环理论建立评估模型。首先，根据OODA作战环分析作战活动，确定侦察预警、指挥控制等能力指标，采用网络层次分析法实现对无人集群作战效能的评估。以对空拦截任务为应用背景，基于能力指标体系建立判断矩阵并根据无权重超矩阵与加权超矩阵获取极限超矩阵下指标权重值。研究结果发现，目标识别概率、决策者知识水平和信息处置速率在效能评估中权重占比较大，分别为16.36%、15.08%和12.64%，提升无人集群作战效能要重点加强对此3个指标的建设力度。所提方法可有效解决装备间多层复杂关联的量化评估问题。

关键词: 网络层次分析法, 无人集群, 作战效能, 观察-判断-决策-行动环

Abstract:

To comprehensively evaluate the combat effectiveness of unmanned swarms, an evaluation model based on the observe-orient-decide-act （OODA） combat loop theory is established. Firstly, combat activities are analyzed through the OODA combat loop to identify capability indicators, including reconnaissance and early warning, command and control, etc. Subsequently, the analytic network process （ANP） is employed to evaluate the combat effectiveness of unmanned swarms. Taking the air defense interception mission as the application scenario, a judgment matrix is constructed based on the capability indicator system. Then, the indicator weight values with the limit super-matrix are obtained using the unweighted super-matrix and weighted super-matrix. The research findings indicate that target recognition probability, decision-maker knowledge level, and information processing rate account for significant weights in effectiveness evaluation, at 16.36%, 15.08%, and 12.64%, respectively. To enhance the combat effectiveness of unmanned swarm systems, priority should be given to strengthening these three key indicators. The proposed method can effectively address the quantitative evaluation problem of multi-level complex correlations between equipment.

Key words: analytic network process (ANP), unmanned swarm, combat effectiveness, observe-orient-decide-act (OODA) loop

中图分类号:

TP 391

路琪, 肖兵, 郭乐江, 周玉萌. 基于网络层次分析法的无人集群作战效能评估[J]. 系统工程与电子技术, 2026, 48(10): 3552-3561.

Qi Lu, Bing Xiao, Lejiang Guo, Yumeng Zhou. Combat effectiveness evaluation of unmanned swarms based on analytic network process[J]. Systems Engineering and Electronics, 2026, 48(10): 3552-3561.

图/表 17

图1

图2

表1

表2

表3

图3

图4

图5

图6

表4

表5

表6

表7

表8

表9

表10

表11

参考文献 32

1	Mao W W, Pang T, Guo Z R, et al. Analysis of the research progress of electromagnetic railgun based on citespace[J]. IEEE Access, 2024, 12, 3499. doi: 10.1109/ACCESS.2023.3349028
2	Wang F, Liu Y, Zhou Y D, et al. An unmanned tank combat game driven by FPSO-MADDPG algorithm[J]. The Journal of Supercomputing, 2024, 80 (15): 21615. doi: 10.1007/s11227-024-06225-3
3	Han Q, Pang B, Li S, et al. Evaluation method and optimization strategies of resilience for air & space defense system of systems based on kill network theory and improved self-information quantity[J]. Defence Technology, 2023, 21, 219. doi: 10.1016/j.dt.2023.01.005
4	明振军, 袁珂, 王国新, 等. 考虑动静态能力的作战体系综合效能评估方法[J]. 北京理工大学学报, 2025, 45(2): 144.
5	赵贝贝, 王方博, 马红侠, 等. 基于系统动力学的无人机集群空战效能评估[J]. 吉林大学学报（信息科学版）, 2025, 43 (2): 327. doi: 10.3969/j.issn.1671-5896.2025.02.016
6	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. doi: 10.16182/j.issn1004731x.joss.21-0225
7	Yu H, Lian D J, Chen G D, et al. Efficiency evaluations of statistical decision probabilities with multiple alternative hypotheses for quality control[J]. GPS Solutions, 2022, 26 (2): 62. doi: 10.1007/s10291-022-01245-z
8	Liu C C, Yu C H, Chen K S. Using statistical test method to establish a decision model of performance evaluation matrix[J]. Applied Sciences, 2023, 13 (8): 5139. doi: 10.3390/app13085139
9	Kuikka V. Probabilistic modelling of system capabilities in operations[J]. Systems, 2023, 11 (3): 115. doi: 10.3390/systems11030115
10	Gui J, Alejano L R, YAO M, et al. GIS-based landslide susceptibility modeling: a comparison between best-first decision tree and its two ensembles （BagBFT and RFBFT）[J]. Remote Sensing, 2023, 15 (4): 1007. doi: 10.3390/rs15041007
11	Tran H, Vu-van T, Bang T, et al. Data mining of formative and summative assessments for improving teaching materials towards adaptive learning: a case study of programming courses at the university level[J]. Electronics, 2023, 12 (14): 3135. doi: 10.3390/electronics12143135
12	Sahlabadi M, Muniyandi R C, Shukur Z, et al. LPMSAEF: lightweight process mining-based software architecture evaluation framework for security and performance analysis[J]. Heliyon, 2024, 10 (5): e26969. doi: 10.1016/j.heliyon.2024.e26969
13	Kenyeres E, Kummer A, Abonyi J. Machine learning classifier-based metrics can evaluate the efficiency of separation systems[J]. Entropy, 2024, 26 (7): 571. doi: 10.3390/e26070571
14	Focassio B M, . Freitas L P, Schleder G R. Performance assessment of universal machine learning interatomic potentials: challenges and directions for materials’ surfaces[J]. ACS Applied Materials & Interfaces, 2025, 17 (9): 13111.
15	Liu G W, Liu J, Wang N, et al. A machine learning-aided framework for hierarchical management of building structural safety[J]. Engineering, Construction and Architectural Management, 2025. DOI:10.1108/ECAM-10-2024-1344.
16	王川川, 陆科宇, 王满喜, 等. 基于杀伤链和网络层次分析法的体系效能评估方法[J]. 舰船电子工程, 2025, 45(4): 146.
17	Wang Y Z, Fu X J, Dong J, et al. Radar intelligent game anti-jamming strategy optimisation based on jamming behaviour inference and active induction[J]. IET Radar, Sonar & Navigation, 2025, 19(1): e70021.
18	张婷婷, 蓝羽石, 宋爱国. 无人集群系统自主协同技术综述[J]. 指挥与控制学报, 2021, 7 (2): 127. doi: 10.12347/j.ycyk.20240314001
19	陈立栋, 王原, 邸建勋, 等. 无人集群协同控制策略及军事应用[J]. 指挥与控制学报, 2023, 9(4): 380.
20	谭跃进, 张小可, 杨克巍. 武器装备体系网络化描述与建模方法[J]. 系统管理学报, 2012, 21 (6): 781. doi: 10.3969/j.issn.1005-2542.2012.06.009
21	张宏, 吴瀚, 朱大鹏. 对作战能力评估标准的认识与思考[J]. 军事运筹与评估, 2024, 39(1): 24.
22	李昌玺, 孙玉彪, 范泽昊, 等. 无人作战平台发展现状及趋势[J]. 中国电子科学研究院学报, 2023, 18 (3): 274.
23	Doull K E, Chalmers C, Fergus P, et al. An evaluation of the factors affecting “Poacher” detection with drones and the efficacy of machine-learning for detection[J]. Sensors, 2021, 21 (12): 4074. doi: 10.3390/s21124074
24	Patton C E, Wickens C D, Clegg B A, et al. How history trails and set size influence detection of hostile intentions[J]. Cognitive Research: Principles and Implications, 2022, 7 (1): 41. doi: 10.1186/s41235-022-00395-5
25	Toroi G I. Rethinking military command and control systems[J]. Bulletin of “Carol I” National Defence University, 2025, 13 (4): 88. doi: 10.53477/2284-9378-24-51
26	Mattingsdal J, Aandal J, Johnsen B H, et al. From peacetime to war: a path analysis of the factors that predict performance among police and military commanders in collaborative crisis response[J]. Frontiers in Psychology, 2023, 14, 1238760. doi: 10.3389/fpsyg.2023.1238760
27	Zak Y, Parmet Y, Oron-gilad T. Facilitating the work of unmanned aerial vehicle operators using artificial intelligence: an intelligent filter for command-and-control maps to reduce cognitive workload[J]. Human Factors: the Journal of the Human Factors and Ergonomics Society, 2023, 65 (7): 1345. doi: 10.1177/00187208221081968
28	Jia L Y, Cai C T, Wang X M, et al. Multi-intent autonomous decision-making for air combat with deep reinforcement learning[J]. Applied Intelligence, 2023, 53 (23): 29076. doi: 10.1007/s10489-023-05058-6
29	Mugnai M, Teppati L M, Satler M, et al. Towards autonomous firefighting UAVs: online planners for obstacle avoidance and payload delivery[J]. Journal of Intelligent & Robotic Systems, 2024, 110 (1): 10.
30	Martino R, Ventre V. An analytic network process to support financial decision-making in the context of behavioral finance[J]. Mathematics, 2023, 11 (18): 3994. doi: 10.3390/math11183994
31	Wolf D E, Louw L, Palm D. An analysis of blockchain versus relational databases for digitalizing information flows in global supply chains using the analytic network process[J]. International Journal of Production Research, 2024, 62 (14): 5016. doi: 10.1080/00207543.2023.2282751
32	Kim Y J, Park B C, Yoon S, et al. Analytic network process-based study of the importance and interconnectivity of facilities under volcanic ash risk[J]. Natural Hazards, 2025, 121 (4): 4155. doi: 10.1007/s11069-024-06963-w

标度	含义
1	两个元素比较，同样重要
3	两个元素比较，前者比后者稍重要
5	两个元素比较，前者比后者明显重要
7	两个元素比较，前者比后者强烈重要
9	两个元素比较，前者比后者极端重要
2,4,6,8	上述相邻判断的中间值
倒数	两个元素比较，后者比前者的重要性标度

$ {e}_{jl} $	$ {e}_{i1} $	$ {e}_{i12} $	···	$ {e}_{i{{n}_{i}}} $	归一化特征向量
$ {e_{i1}} $	$ a_{11}^{(jl)} $	$ a_{12}^{(jl)} $	$ \cdots $	$ a_{1{n_i}}^{(jl)} $	$ {\boldsymbol{w}}_{i1}^{(jl)} $
$ {e_i}_2 $	$ a_{12}^{(jl)} $	$ a_{22}^{(jl)} $	$ \cdots $	$ a_{2{n_i}}^{(jl)} $	$ {\boldsymbol{w}}_{i2}^{(jl)} $
$ \vdots $	$ \vdots $	$ \vdots $	$ \ddots $	$ \vdots $	$ \vdots $
$ {e_{i{n_i}}} $	$ a_{1{n_i}}^{(jl)} $	$ a_{2{n_i}}^{(jl)} $	$ \cdots $	$ a_{{n_i}{n_i}}^{(jl)} $	$ {\boldsymbol{w}}_{i{n_i}}^{(jl)} $

$ {C}_{j} $	$ {C}_{1} $	$ {C}_{2} $	···	$ {C}_{{N}} $	归一化特征向量
${C_1}$	$ a_{11}^{(j)} $	$ a_{12}^{(j)} $	$ \cdots $	$ a_{1N}^{(j)} $	$ {\boldsymbol{w}}_1^{(j)} $
${C_2}$	$ a_{12}^{(j)} $	$ a_{22}^{(j)} $	$ \cdots $	$ a_{2N}^{(j)} $	$ {\boldsymbol{w}}_2^{(j)} $
$ \vdots $	$ \vdots $	$ \vdots $	$ \ddots $	$ \vdots $	$ \vdots $
${C_{{N}}}$	$ a_{1N}^{(j)} $	$ a_{2N}^{(j)} $	$ \cdots $	$ a_{NN}^{(j)} $	$ {\boldsymbol{w}}_N^{(j)} $

次准则	$ {e}_{31} $	$ {e}_{32} $	$ {e}_{33} $
$ {e}_{31} $	1	3	1/3
$ {e}_{32} $	1/3	1	1/5
$ {e}_{33} $	3	5	1

次准则	$ {e}_{31} $	$ {e}_{32} $	$ {e}_{33} $
$ {e}_{31} $	1	3	1/3
$ {e}_{32} $	1/3	1	1/4
$ {e}_{33} $	3	4	1