面向任务的智能化装备体系作战效能评估模型

doi:10.16182/j.issn1004731x.joss.26-0128

摘要/Abstract

摘要：

针对复杂对抗环境下智能装备体系作战仿真的层级决策割裂、算法指标与作战效能映射不清、仿真模型缺乏自适应演化能力等问题，提出一种分层演化自适应学习（hierarchical evolutionary adaptive learning， HEAL）框架。遵循“微观-中观-宏观”的系统分层建模思想，构建融合单装鲁棒自主决策、系统网络涌现协同与体系策略博弈演化的多层学习结构，通过自下而上的行为归纳与自上而下的规则塑形相结合，实现学习策略、协同结构与体系作战效能之间的跨层闭环耦合，建立算法指标向作战效能指标的可解释映射关系。仿真结果表明：与单层或弱耦合学习方法相比，HEAL框架能够提升体系任务成功率与协同一致性，并有效抑制复杂扰动条件下的效能退化。为智能化装备体系的分层建模、协同学习与作战效能仿真评估提供了一种统一且可验证的方法框架。

关键词: 智能化装备体系, 分层演化自适应学习, 系统仿真, 随机博弈, 作战效能评估, 协同涌现

Abstract:

A hierarchical evolutionary adaptive learning (HEAL) framework is proposed to address the problems in the operational simulation of intelligent equipment systems under complex adversarial environments, including fragmented hierarchical decision-making, unclear mapping between algorithmic indicators and operational effectiveness, and the lack of adaptive evolution capability of simulation models. A multi-layer learning architecture that integrates robust autonomous decision-making for single units, emergent collaboration of system networks, and game-theoretic evolution of system-of-systems strategies is constructed by following the “micro-meso-macro” system-oriented hierarchical modeling paradigm. A cross-layer closed-loop coupling among learned policies, cooperative structures, and operational effectiveness is achieved by combining bottom-up behavioral abstraction with top-down rule shaping, thereby establishing an interpretable mapping relationship from algorithmic indicators to operational effectiveness indicators. Simulation results demonstrate that compared with single-layer or weakly coupled learning methods, the HEAL framework significantly improves the mission success rate and collaboration consistency, while effectively mitigating effectiveness degradation under complex disturbances. A unified and verifiable methodological framework is provided for hierarchical modeling, collaborative learning, and simulation-based evaluation of operational effectiveness for intelligent equipment systems.

Key words: intelligent equipment system, hierarchical evolutionary adaptive learning, system simulation, stochastic game, operational effectiveness evaluation, emergent collaboration

中图分类号:

TP18

张龙,黄文博,冯轩铭等 . 面向任务的智能化装备体系作战效能评估模型[J]. 系统仿真学报, 2026, 38(10): 2819-2839.

Zhang Long,Huang Wenbo,Feng Xuanming,et al . Mission-oriented Combat Effectiveness Evaluation Model for Intelligent Equipment System-of-systems[J]. Journal of System Simulation, 2026, 38(10): 2819-2839.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

参考文献 34

[1]	熊丽琴, 陈希亮, 赖俊, 等. 面向关系建模的合作多智能体深度强化学习综述[J]. 计算机工程与应用, 2025, 61(18): 41-60.
	Xiong Liqin, Chen Xiliang, Lai Jun, et al. Survey of Cooperative Multi-agent Deep Reinforcement Learning Based on Relational Modeling[J]. Computer Engineering and Applications, 2025, 61(18): 41-60.
[2]	罗彪, 胡天萌, 周育豪, 等. 多智能体强化学习控制与决策研究综述[J]. 自动化学报, 2025, 51(3): 510-539.
	Luo Biao, Hu Tianmeng, Zhou Yuhao, et al. Survey on Multi-agent Reinforcement Learning for Control and Decision-making[J]. Acta Automatica Sinica, 2025, 51(3): 510-539.
[3]	Liu Yu, Li Zhi, Jiang Zhizhuo, et al. Prospects for Multi-agent Collaboration and Gaming: Challenge, Technology, and Application[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23(7): 1002-1010.
[4]	王刚桥, 邢邗, 陈永强, 等. 深度不确定环境下的系统仿真方法研究[J]. 系统工程理论与实践, 2024, 44(2): 444-465.
	Wang Gangqiao, Xing Han, Chen Yongqiang, et al. Research on System Simulation Approach Under Deep Uncertainty[J]. Systems Engineering-theory & Practice, 2024, 44(2): 444-465.
[5]	Pu Zhiqiang, Wang Huimu, Liu Zhen, et al. Attention Enhanced Reinforcement Learning for Multi-agent Cooperation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(11): 8235-8249.
[6]	Park Soohyun, Pyoung Kim Jae, Park Chanyoung, et al. Quantum Multi-agent Reinforcement Learning for Autonomous Mobility Cooperation[J]. IEEE Communications Magazine, 2024, 62(6): 106-112.
[7]	刘洋, 李妮, 于泽熙, 等. 融合大语言模型技术的飞机编队行为智能建模[J/OL]. 航空学报. (2026-01-12) [2026-01-31]. .
	Liu Yang, Li Ni, Yu Zexi, et al. An Intelligent Modeling Method for Aircraft Formation Behaviors Integrating LLM Technology[J/OL]. Acta Aeronautica et Astronautica Sinica. (2026-01-12) [2026-01-31]. .
[8]	汪江鹏, 杨萍, 汪民乐, 等. 基于协同和网络效应的作战体系效能评估方法[J]. 系统工程与电子技术, 2025, 47(11): 3754-3764.
	Wang Jiangpeng, Yang Ping, Wang Minle, et al. Combat System Effectiveness Evaluation Method Based on Coordination and Network Effects[J]. Systems Engineering and Electronics, 2025, 47(11): 3754-3764.
[9]	赵海燕, 周峰, 杨文静, 等. 数据驱动下的反导装备体系效能评估建模与仿真[J]. 国防科技大学学报, 2025, 47(3): 81-89.
	Zhao Haiyan, Zhou Feng, Yang Wenjing, et al. Data-driven Effectiveness Evaluation Modeling and Simulation of Anti-missile Equipment System[J]. Journal of National University of Defense Technology, 2025, 47(3): 81-89.
[10]	Li Z, Yang Y, Cheng H. Efficient Multi-agent Cooperation: Scalable Reinforcement Learning with Heterogeneous Graph Networks and Limited Communication[J]. Knowledge-Based Systems, 2024, 300: 112124.
[11]	Gong Yalei, Xiong Hongyun, Li Mengmeng, et al. Reinforcement Learning for Multi-agent Formation Navigation with Scalability[J]. Applied Intelligence, 2023, 53(23): 28207-28225.
[12]	Liu Haiying, Li Zhihao, Huang Kuihua, et al. Evolutionary Reinforcement Learning Algorithm for Large-scale Multi-agent Cooperation and Confrontation Applications[J]. The Journal of Supercomputing, 2024, 80(2): 2319-2346.
[13]	Liu Shanqi, Liu Weiwei, Chen Wenzhou, et al. Learning Multi-agent Cooperation via Considering Actions of Teammates[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(8): 11553-11564.
[14]	Zhao Juan, Zhu Tong, Xiao Shuo, et al. Actor-critic for Multi-agent Reinforcement Learning with Self-attention[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2022, 36(9): 2252014.
[15]	Jiang Yuannan, Jiang Shengming, Wang Xiaofeng. A Model-based Reinforcement Learning Algorithm for Multi-agent Cooperation Nash Equilibrium with Unstable Communication[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2024, 71(11): 4743-4747.
[16]	Zhao Liyang, Chang Tianqing, Zhang Lei, et al. Multi-agent Cooperation Policy Gradient Method Based on Enhanced Exploration for Cooperative Tasks[J]. International Journal of Machine Learning and Cybernetics, 2024, 15(4): 1431-1452.
[17]	Rao Jinjun, Wang Cong, Liu Mei, et al. ISFORS-MIX: Multi-agent Reinforcement Learning with Importance-sampling-free Off-policy Learning and Regularized-softmax Mixing Network[J]. Knowledge-Based Systems, 2025, 309: 112881.
[18]	王建峰, 贾高伟, 郭正, 等. 多无人机协同任务规划方法研究综述[J]. 系统工程与电子技术, 2024, 46(10): 3437-3450.
	Wang Jianfeng, Jia Gaowei, Guo Zheng, et al. Review of Research on Multi-UAV Collaborative Mission Planning Method[J]. Systems Engineering and Electronics, 2024, 46(10): 3437-3450.
[19]	王辉雄, 洪东跑, 刘宸宁, 等. 武器装备智能保障系统建模与效能分析[J]. 宇航学报, 2023, 44(2): 197-207.
	Wang Huixiong, Hong Dongpao, Liu Chenning, et al. Modeling and Efficiency Analysis for Intelligent Weapon Equipment Support System[J]. Journal of Astronautics, 2023, 44(2): 197-207.
[20]	李峻森, 方依宁, 张云安, 等. 面向任务的装备保障体系多Agent建模与评估方法[J]. 系统工程与电子技术, 2023, 45(1): 279-290.
	Li Junsen, Fang Yining, Zhang Yunan, et al. Multi-agent Modeling and Evaluation Method for Mission-oriented Equipment Support SoS[J]. Systems Engineering and Electronics, 2023, 45(1): 279-290.
[21]	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1): 155-161.
	Liu Zunfei, Zou Bo, Chen Xulin, 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.
[22]	Liu Weiwei, Jing Wei, Liu Shanqi, et al. Expert Demonstrations Guide Reward Decomposition for Multi-agent Cooperation[J]. Neural Computing and Applications, 2023, 35(27): 19847-19863.
[23]	Ren Yixiang, Ye Zhenhui, Chen Yining, et al. Soft-HGRNs: Soft Hierarchical Graph Recurrent Networks for Multi-agent Partially Observable Environments[J]. Frontiers of Information Technology & Electronic Engineering, 2023, 24(1): 117-130.
[24]	Wang C, Durugkar I, Liebman E, et al. DM²: Decentralized Multi-agent Reinforcement Learning Via Distribution Matching[C]//Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence. [S.l.]: AAAI Press, 2023: 11699-11707.
[25]	Wang Ni, Das G P, Millard A G. Learning Cooperative Behaviours in Adversarial Multi-agent Systems[C]//Towards Autonomous Robotic Systems. Cham: Springer International Publishing, 2022: 179-189.
[26]	Wang Qianhui, Wang Xinzhi, Gao Mingke, et al. Fully Parameterized Dueling Mixing Distributional Q-learning for Multi-agent Cooperation[C]//2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI). Piscataway: IEEE, 2022: 1147-1151.
[27]	Kong He, Xing Qianli, Wang Qi, et al. ADAC: Actor-double-attention-critic for Multi-agent Cooperation in Mixed Cooperative-competitive Environments[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(7): 9579-9592.
[28]	Xu Chenhang, Wang Jia, Zhu Xiaohui, et al. Decentralized Multi-agent Cooperation Via Adaptive Partner Modeling[J]. Complex & Intelligent Systems, 2024, 10(4): 4989-5004.
[29]	Tan Siyang, Chen Binqiang. Attentional Opponent Modelling for Multi-agent Cooperation[C]//2023 International Joint Conference on Neural Networks (IJCNN). Piscataway: IEEE, 2023: 1-9.
[30]	Chen Yiqun, Yang Wei, Zhang Tianle, et al. Commander-soldiers Reinforcement Learning for Cooperative Multi-agent Systems[C]//2022 International Joint Conference on Neural Networks (IJCNN). Piscataway: IEEE, 2022: 1-7.
[31]	Liu Boyin, Pu Zhiqiang, Gao Junlong, et al. Tacit Commitments Emergence in Multi-agent Reinforcement Learning[C]//Neural Information Processing. Cham: Springer International Publishing, 2023: 27-36.
[32]	付一阳, 胡博, 刘人鹏, 等. 星地融合网络中基于异质图表征的多智能体协作切换方法[J]. 计算机学报, 2026, 49(2): 347-364.
	Fu Yiyang, Hu Bo, Liu Renpeng, et al. A Multi-agent Heterogeneous Graph Representation-based Handover Method in Satellite-terrestrial Integrated Network[J]. Chinese Journal of Computers, 2026, 49(2): 347-364.
[33]	熊骏, 张文博, 熊智, 等. 多智能体协同路径规划综述[J]. 系统仿真学报, 2025, 37(12): 3033-3049.
	Xiong Jun, Zhang Wenbo, Xiong Zhi, et al. Survey of Cooperative Multi-agent Path Finding[J]. Journal of System Simulation, 2025, 37(12): 3033-3049.
[34]	张华卿, 张晓飞, 郝明瑞, 等. 鲁棒多智能体协同对抗策略离线强化学习[J]. 系统工程与电子技术, 2026, 48(5): 1670-1681.
	Zhang Huaqing, Zhang Xiaofei, Hao Mingrui, et al. Robust Multi-agent Cooperative Confrontation Policy Offline Reinforcement Learning[J]. Systems Engineering and Electronics, 2026, 48(5): 1670-1681.