基于图卷积的陆域智能化无人作战体系效能评估

doi:10.12382/bgxb.2024.0516

摘要/Abstract

摘要：

针对陆域智能化无人作战体系效能评估中存在的系统性不足、关联性缺乏以及高度复杂性考虑不足等问题,提出了一种基于图卷积神经网络(Graph Convolutional Networks,GCN)的陆域智能化无人作战体系效能评估框架,旨在通过利用GCN技术对智能化无人作战体系效能进行精确评估。针对陆域智能化作战特点建立了一套智能化作战的评估指标体系,并将该体系映射到图网络结构上,实现对无人作战体系在复杂作战环境中的高度抽象表示;采用大数据分析技术与专家经验知识对初始数据集进行预处理和特征工程,以优化输入数据的质量;通过应用GCN的半监督学习模式,深入挖掘指标体系的层次结构及其各组成部分之间的相互关联,实现对陆域智能化无人作战体系效能的综合评估。该评估框架针对目前陆域智能化无人作战体系效能评估中存在的诸多问题,提供了一种动态性强、系统化全面的解决方案,展示了GCN在军事科技领域的应用潜力。

关键词: 无人作战, 陆域智能化, 效能评估, 图卷积神经网络, 大数据

Abstract:

To address the issues of systemic inadequacies, lack of correlation, and insufficient consideration of complexity in the effectiveness evaluation of land-based intelligent unmanned combat systems, a graph convolutional network (GCN)-based effectiveness evaluationframework is proposed. The framework aims to leverage GCN technology to precisely evaluate the performance of intelligent unmanned combat systems. A comprehensive set of evaluation index systemis established according to the characteristics of land-based intelligent combat, and this system is mapped onto a graph network structure, enabling a highly abstract representation of the unmanned combat system in complex operational environments. The big data analytics and expert knowledge areused to preprocess and engineer the initial dataset for optimizing the quality of input data. The hierarchical structure of the evaluation index system and the interrelationships among its components are deeply explored by applying GCN’s semi-supervised learning mode, thereby achieving a comprehensive evaluation of the effectiveness of land-based intelligent unmanned combat systems. This evaluation framework addresses numerous issues existingin the current evaluation of these systems, offering a dynamic, systematic, and comprehensive solution that demonstrates the application potential of GCN in the field of military technology.

Key words: unmanned combat, land-based intelligent combat, effectiveness evaluation, graph convolutional network, big data

中图分类号:

E917

万张博, 胡建刚, 李俊杰, 陈励, 毛余琨, 叶梦雅. 基于图卷积的陆域智能化无人作战体系效能评估[J]. 兵工学报, 2024, 45(S1): 271-277.

WAN Zhangbo, HU Jiangang, LI Junjie, CHEN Li, MAO Yukun, YE Mengya. Effectiveness Evaluation of Land-based Intelligent Unmanned Combat Systems Based on Graph Convolutional Networks[J]. Acta Armamentarii, 2024, 45(S1): 271-277.

图/表 6

图1 基于大数据的智能化无人作战体系效能评估技术框架

Fig.1 Technical framework for evaluating the effectiveness of jntelligent unmanned combat system based on big data

图2 智能化无人作战效能指标体系

Fig.2 Intelligent unmanned combat effectiveness index system

图3 基于半监督学习的GCN的智能化无人作战体系效能评估方法框架

Fig.3 Methodological framework for evaluating the effectiveness of jntelligent unmanned combat systems based on semi-supervised learning of GCNs

图4 指标体系转化映射

Fig.4 Mapping of index systems

图5 数据预处理

Fig.5 Data preprocessing

图6 图卷积和聚合

Fig.6 Graph convolution and aggregation

参考文献 15

[1]	常会振, 秦大国, 孙盛智, 等. 基于ADC模型优化的海上无人机作战效能评估[J]. 兵器装备工程学报, 2023, 44(9):58-68.
	CHANG H Z, QIN D G, SUN S Z, et al. Operational effectiveness evaluation of maritime unmanned aerial vehicle based on ADC model optimization[J]. Journal of Ordnance Equipment Engineering, 2023, 44(9): 58-68. (in Chinese)
[2]	CHANG H Y, ZHANG R, ZHANG Y. The evaluation of information contribution for unmanned aerial vehicle integrating into the air combat system[C]// Proceedings of the 2022 IEEE International Conference on Unmanned Systems. Guangzhou, China: IEEE, 2022: 681-687.
[3]	吴志飞, 肖丁, 张立. “集对-指数法”的水面舰艇作战能力评估[J]. 火力与指挥控制, 2013, 38(9):101-103.
	WU Z F, XIAO D, ZHANG L. Research on surface warship combat capability evaluation based on set pair analysis and index method[J]. Fire Control & Command Control 2013, 38(9):101-103. (in Chinese)
[4]	史睿冰, 姚兴太, 史圣兵, 等. 基于层次分析法的通信系统效能评估[J]. 计算机工程与设计, 2013, 34(12):4131-4136.
	SHI R B, YAO X T, SHI S B, et al. Effectiveness evaluation of communication system based on AHP[J]. Computer Engineering and Design, 2013, 34(12):4131-4136. (in Chinese)
[5]	唐政, 孙超, 刘宗伟, 等. 基于灰色层次分析法的水声对抗系统效能评估[J]. 兵工学报, 2012, 33(4):432-436.
	TANG Z, SUN C, LIU Z W, et al. Research on efficiency evaluation for underwater acoustic countermeasure system based on grey hierarchy analysis[J]. Acta Armamentarii, 2012, 33(4): 432-436. (in Chinese)
[6]	LI H, XING J S. Combat effectiveness evaluation method of photoelectric defense system based on BP neural network optimized by bat algorithm[C]// Proceedings of the 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer. Shenyang, China: IEEE, 2013: 2481-2485.
[7]	刘遵飞, 邹波, 陈续麟, 等. 有人与无人联合作战模式下的装备体系结构建模与效能评估[J]. 兵工学报, 2022, 43(增刊1):155-161.
	LIU Z F, ZOU B, CHEN X L, et al. Architecture modeling and effectiveness evaluation of equipment system under manned and unmanned joint operation mode[J]. Acta Armamentarii, 2022, 43(S1): 155-161. (in Chinese) doi: 10.12382/bgxb.2022.A027
[8]	DUAN L D, SHI H Y, LIN Z C, et al. Evaluation method of UAV’s contribution degree to army aviation combat system based on MMF and ANP[C]// Proceedings of the 2020 12th International Conference on Intelligent Human-Machine Systems and Cybernetics. Hangzhou, China: IEEE, 2020: 261-264.
[9]	杨梓鑫, 薛源, 孙畅, 等. 基于Elman神经网络和Copula函数的多维装备效能评估模型[J]. 兵工学报, 2020, 41(8):1633-1645. doi: 10.3969/j.issn.1000-1093.2020.08.018
	YANG Z X, XUE Y, SUN C, et al. Multidimensional equipment effectiveness evaluation model based on Elman neural network and Copula function[J]. Acta Armamentarii, 2020, 41(8): 1633-1645. (in Chinese) doi: 10.3969/j.issn.1000-1093.2020.08.018
[10]	DUAN L D, WANG M, LIN Z C, et al. Research on evaluation method of UAV’s contribution degree to army aviation combat system based on simulation deduction[C]// Proceedings of the 2021 33rd Chinese Control and Decision Conference. Kunming, China: IEEE, 2021: 2580-2585.
[11]	FANG J Y, ZHANG W M, MANG H B, et al. A method for generating small sample data and evaluating the effectiveness of combat weapons based on conditional adversarial nets[C]// Proceedings of the 2023 2nd International Conference on Artificial Intelligence and Computer Information Technology. Yichang, China: IEEE, 2023: 1-6.
[12]	QUAN W, JIA L P, ZHANG Z, et al. A multi-dimensional dynamic evaluation method for the intelligence of unmanned aerial vehicle swarm[C]// Proceedings of the 2023 IEEE International Conference on Unmanned Systems. Hefei, China: IEEE, 2023: 731-737.
[13]	DING Y M, ZHU M, LU Q. Effectiveness evaluation of underwater swarm combat based on FAHP and GA-Elman neural network[C]// Proceedings of the 2019 Chinese Automation Congress. Hangzhou, China: IEEE, 2019: 106-110.
[14]	丁伟, 明振军, 王国新, 等. 基于多层次LSTM网络的多智能体攻防效能动态预测模型[J]. 兵工学报, 2023, 44(1):176-192. doi: 10.12382/bgxb.2022.0192
	DING W, MING Z J, WANG G X, et al. Dynamic prediction model based on multi-level LSTM network for multi-agent attack and defense effectiveness[J]. Acta Armamentarii, 2023, 44(1): 176-192. (in Chinese) doi: 10.12382/bgxb.2022.0192
[15]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[R/OL]. Ithaca, NY, US: Cornell University, 2016. https://arxiv.org/abs/1609.02907.