面向智能自主识别的反舰导弹作战效能评估

doi:10.16182/j.issn1004731x.joss.25-0981

摘要/Abstract

摘要：

针对现有识别模型静态融合策略自适应差、评估体系单一且与动态对抗需求脱节的问题，构建了面向实战的“识别精准度-抗干扰稳度-决策时效性-模态互补性”四维评估体系，并提出可动态适配战术想定的作战效能综合指数(operational effectiveness composite index， OECI)。设计了一种面向复杂对抗环境的反舰导弹多模态动态注意力融合网络MDA-Net。通过异质特征解耦、交叉模态注意力动态加权与层级化门控决策机制，实现了干扰环境下多源信息可靠性的自主评估与自适应融合。仿真实验表明：在模拟的强对抗及模态缺失场景下，MDA-Net的OECI显著优于传统多层感知机与卷积神经网络基线模型，表现出优异的综合识别性能、抗干扰韧性与环境适应性。构建的“评估体系-识别模型-战术适配”完整范式为反舰导弹智能识别系统的设计与效能评估提供了系统的理论方法与技术支撑。

关键词: 反舰导弹, 自主识别, 多模态融合, 特征工程, 效能评估, 智能化作战

Abstract:

To address the core issues of poor adaptability of static fusion strategies in existing recognition models, as well as the simplistic evaluation system and its disconnection from dynamic confrontation requirements, a practical four-dimensional evaluation system encompassing "recognition accuracy, anti-jamming stability, decision timeliness, and modal complementarity" was constructed, and an operational effectiveness composite index (OECI) capable of dynamically adapting to tactical scenarios was proposed. A multimodal dynamic attention fusion network (MDA-Net) for anti-ship missiles in complex confrontation environments was designed. Through heterogeneous feature decoupling, dynamic weighting of cross-modal attention, and a hierarchical gating decision mechanism, the autonomous evaluation and adaptive fusion of multi-source information reliability under jamming environments were realized. Simulation experiments indicate that under simulated high-intensity confrontation and modal missing scenarios, the OECI of MDA-Net significantly outperforms the baseline models of traditional multi-layer perceptron and convolutional neural networks, exhibiting excellent comprehensive recognition performance, anti-jamming resilience, and environmental adaptability. The constructed complete paradigm of "evaluation system, recognition model, and tactical adaptation" provides a systematic theoretical method and technical support for the design and effectiveness evaluation of intelligent recognition systems for anti-ship missiles.

Key words: anti-ship missile, autonomous recognition, multimodal fusion, feature engineering, effectiveness evaluation, intelligent combat

中图分类号:

E927.7

张龙,冯轩铭,雷震等 . 面向智能自主识别的反舰导弹作战效能评估[J]. 系统仿真学报, 2026, 38(8): 2407-2424.

Zhang Long,Feng Xuanming,Lei Zhen,et al . Combat Effectiveness Evaluation of Anti-ship Missiles for Intelligent Autonomous Recognition[J]. Journal of System Simulation, 2026, 38(8): 2407-2424.

图/表 12

图1

图2

图3

图4

表1

图5

图6

图7

表2

不同作战想定下各模型的OECI值与排名

作战想定	权重配置( $w a, w r, w t, w m$ )	MDA-Net	Baseline-CNN	Baseline-MLP
精准狙杀	(0.5, 0.2, 0.2, 0.1)	0.781 5/1	0.693 2/2	0.674 5/3
强对抗突防	(0.2, 0.5, 0.15, 0.15)	0.753 8/1	0.631 7/2	0.610 9/3
协同饱和攻击	(0.3, 0.3, 0.3, 0.1)	0.765 2/1	0.668 9/2	0.657 3/3
复杂环境适应	(0.25, 0.25, 0.2, 0.3)	0.772 4/1	0.620 8/2	0.598 7/3

表2

图8

图9

图10

参考文献 39

[1]	肖轩, 李松阳, 王多治, 等. 反舰导弹突防水面舰艇多层防空体系效能评估[J]. 舰船电子工程, 2024, 44(10): 17-20, 36.
	Xiao Xuan, Li Songyang, Wang Duozhi, et al. Effectiveness Evaluation of Anti-ship Missiles Penetrating Multilayer Air Defense System of Surface Ship[J]. Ship Electronic Engineering, 2024, 44(10): 17-20, 36.
[2]	韩晓, 王晓楠. 反舰导弹导引头抗干扰技术发展趋势分析[J]. 舰船电子对抗, 2024, 47(4): 24-30, 54.
	Han Xiao, Wang Xiaonan. Analysis on the Development Trend of Anti-jamming Technology of Anti-ship Missile Seeker[J]. Shipboard Electronic Countermeasure, 2024, 47(4): 24-30, 54.
[3]	吴璠, 王俊伟, 胡冬冬, 等. 2024年国外飞航导弹发展综述[J]. 战术导弹技术, 2025(2): 1-8.
	Wu Fan, Wang Junwei, Hu Dongdong, et al. Review of Foreign Cruise Missile Developments in 2024[J]. Tactical Missile Technology, 2025(2): 1-8.
[4]	Deng Tianbo, Huang Hao, Fang Yangwang, et al. Reinforcement Learning-based Missile Terminal Guidance of Maneuvering Targets with Decoys[J]. Chinese Journal of Aeronautics, 2023, 36(12): 309-324.
[5]	Yang G, Fang Y, Ma W, et al. Cooperative Trajectory Shaping Guidance Law for Multiple Anti-ship Missiles[J]. The Aeronautical Journal, 2024, 128(1319): 73-91.
[6]	Liu Gang, Lao Songyang, Hou Lülin, et al. OARPER-MAFO Algorithm for Anti-ship Missile Path Planning[J]. Aerospace Science and Technology, 2015, 47: 135-145.
[7]	Jang Hyesu, Yang Wooseong, Kim Hanguen, et al. MOANA: Multi-radar Dataset for Maritime Odometry and Autonomous Navigation Application[J]. The International Journal of Robotics Research, 2026, 45(2): 193-203.
[8]	Wang Feng, Qu Qiankun, Yang Hao, et al. Current Status and Prospects of Guidance Techniques for Intercepting Hypersonic Glide Vehicles: A Review[J]. Defence Technology, 2026, 58: 241-259.
[9]	林立, 胡生亮, 吴林罡, 等. LRASM反舰导弹发展态势与对抗手段探析[J]. 战术导弹技术, 2025(3): 30-38.
	Lin Li, Hu Shengliang, Wu Lingang, et al. Analysis of the Development Trend and Countermeasures of LRASM[J]. Tactical Missile Technology, 2025(3): 30-38.
[10]	Gaudet B, Furfaro R. Terminal Adaptive Guidance for Autonomous Hypersonic Strike Weapons via Reinforcement Metalearning[J]. Journal of Spacecraft and Rockets, 2023, 60(1): 286-298.
[11]	Zhang Yaozhong, Ding Meiyan, Du Yu, et al. AAV Swarm Intelligent Interception Driven by Mission-empowered Mean-field Gate Recurrent Reinforcement Learning[J]. IEEE Transactions on Aerospace and Electronic Systems, 2025, 61(3): 6373-6389.
[12]	Wright D, Tracy C L. Hypersonic Weapons: Vulnerability to Missile Defenses and Comparison to MaRVs[J]. Science & Global Security, 2023, 31(3): 68-114.
[13]	Su Jintao, Zhang Hua, Yao Yunqi. Design of Anti-submarine Warfare Module for Unmanned Surface Vehicle[C]//2020 3rd International Conference on Unmanned Systems (ICUS). Piscataway: IEEE, 2020: 342-345.
[14]	Chitsaz Ali, Naghash Abolghasem, Farhad Fani Saberi, et al. Integration of Seeker Filter, Guidance and Control for Exact High-velocity Target Interception[J]. Scientific Reports, 2025, 15(1): 41060.
[15]	Wei Chuheng, Qin Ziye, Zhang Ziyan, et al. Integrating Multi-modal Sensors: A Review of Fusion Techniques for Intelligent Vehicles[C]//2025 IEEE Intelligent Vehicles Symposium (Ⅳ). Piscataway: IEEE, 2025: 1817-1824.
[16]	Sinha Abhijit, Chen Huimin, Danu D G, et al. Estimation and Decision Fusion: A Survey[J]. Neurocomputing, 2008, 71(13/15): 2650-2656.
[17]	Shi Kun, He Shibo, Shi Zhenyu, et al. Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey[J]. IEEE Communications Surveys & Tutorials, 2026, 28: 3478-3520.
[18]	Ekundayo Olufisayo S, Absalom E Ezugwu. Deep Learning: Historical Overview from Inception to Actualization, Models, Applications and Future Trends[J]. Applied Soft Computing, 2025, 181: 113378.
[19]	Khromchenko O. Artificial Intelligence and Scientific Research[C]//Integrity, Open Science and Artificial Intelligence in Academia and Beyond:Meeting at the Crossroads. Riga: Baltija Publishing, 2023: 43-45.
[20]	Adate A, Tripathy B K. A Survey on Deep Learning Methodologies of Recent Applications[M]//Debi Prasanna Acharjya, Anirban Mitra, Noor Zaman. Deep Learning in Data Analytics: Recent Techniques, Practices and Applications. Cham: Springer International Publishing, 2022: 145-170.
[21]	Rashidi Hooman H, Pantanowitz Joshua, Hanna Matthew G, et al. Introduction to Artificial Intelligence and Machine Learning in Pathology and Medicine: Generative and Nongenerative Artificial Intelligence Basics[J]. Modern Pathology, 2025, 38(4): 100688.
[22]	Raman Raghu, Kowalski R, Achuthan Krishnashree, et al. Navigating Artificial General Intelligence Development: Societal, Technological, Ethical, and Brain-inspired Pathways[J]. Scientific Reports, 2025, 15(1): 8443.
[23]	Amini Mitra, Nandi Veena, Morande Swapnil, et al. Steering Generative AI Toward Beneficence: A Review of Constructive Deepfake Applications[M]. Hershey: IGI Global, 2024: 283-294.
[24]	Iudice Ivan, Pascarella Domenico, Corraro Gianluca, et al. A Real/Fast-time Simulator for Impact Assessment of Spoofing & Jamming Attacks on GNSS Receivers[C]//2024 11th International Workshop on Metrology for AeroSpace (MetroAeroSpace). Piscataway: IEEE, 2024: 309-314.
[25]	Aref M A, Jayaweera S K, Machuzak S. Multi-agent Reinforcement Learning Based Cognitive Anti-jamming[C]//2017 IEEE Wireless Communications and Networking Conference (WCNC). Piscataway: IEEE, 2017: 1-6.
[26]	Ma Chen, Wang Ningfei, Zhao Zhengyu, et al. ControlLoc: Physical-world Hijacking Attack on Camera-based Perception in Autonomous Driving[C]//Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security. New York: Association for Computing Machinery, 2025: 738-752.
[27]	Chow K H, Liu Ling, Loper M, et al. Adversarial Objectness Gradient Attacks in Real-time Object Detection Systems[C]//2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA). Piscataway: IEEE, 2020: 263-272.
[28]	李哲, 王可, 王彪, 等. 人机融合智能决策:概念、框架与应用[J]. 电子与信息学报, 2025, 47(10): 3439-3464.
	Li Zhe, Wang Ke, Wang Biao, et al. Human-machine Fusion Intelligent Decision-making: Concepts, Framework, and Applications[J]. Journal of Electronics & Information Technology, 2025, 47(10): 3439-3464.
[29]	Park Jongyoon, Kim Pileun, Ko Daeil. Real-time Open-vocabulary Perception for Mobile Robots on Edge Devices: A Systematic Analysis of the Accuracy-latency Trade-off[J]. Frontiers in Robotics and AI, 2025, 12: 1693988.
[30]	Atzmon Dor, Stern Roni, Felner Ariel, et al. Robust Multi-agent Path Finding[C]//Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. Richland: International Foundation for Autonomous Agents and Multiagent Systems, 2018: 1862-1864.
[31]	Pawlicki Marek, Pawlicka Aleksandra, Uccello Federica, et al. Evaluating the Necessity of the Multiple Metrics for Assessing Explainable AI: A Critical Examination[J]. Neurocomputing, 2024, 602: 128282.
[32]	Bakhshi Javad, Efatmaneshnik Mahmoud. The Interplay of Capability and Complexity in Military Context: Definitions, Challenges, and Implications[J]. Defence Studies, 2025, 25(1): 133-162.
[33]	Xie Songjie, He Hengtao, Song Shenghui, et al. Toward Real-time Edge AI: Model-agnostic Task-oriented Communication with Visual Feature Alignment[J]. IEEE Journal on Selected Areas in Communications, 2025, 43(12): 4262-4276.
[34]	王凌云, 吴桐, 王敬哲, 等. 基于CNN-SENet和特征融合的非侵入式负荷辨识方法[J/OL]. 信息与控制. (2025-08-27) [2025-10-11]. .
	Wang Lingyun, Wu Tong, Wang Jingzhe, et al. A Non-intrusive Load Identification Method Based on CNN-SENet and Feature Fusion[J/OL]. Information and Control. (2025-08-27) [2025-10-11]. .
[35]	刘善文. 基于博弈论的对抗图像分类网络鲁棒泛化性的研究与应用[D]. 成都: 四川师范大学, 2025.
	Liu Shanwen. Research and Application on Robust Generalization in Adversarial Image Classification Networks Based on Game Theory[D]. Chengdu: Sichuan Normal University, 2025.
[36]	赵文硕, 张帅, 王轩瀚, 等. 面向对抗鲁棒的信号识别设计方法[J]. 电子科技大学学报, 2025, 54(4): 618-625.
	Zhao Wenshuo, Zhang Shuai, Wang Xuanhan, et al. Design Method for Signal Modulation Recognition Oriented to Adversarial Robustness[J]. Journal of University of Electronic Science and Technology of China, 2025, 54(4): 618-625.
[37]	刘玉杰, 王一雯. 基于多模态协同增强的微姿态识别方法[J/OL]. 计算机工程. (2025-08-28) [2025-10-11]. .
	Liu Yujie, Wang Yiwen. Micro Gesture Recognition Method Based on Multi-modal Collaborative Enhancement[J/OL]. Computer Engineering. (2025-08-28) [2025-10-11]. .
[38]	刘仲民, 刘洋, 胡文瑾. 联合门控注意力与残差密集Transformer的壁画修复算法[J]. 红外与激光工程, 2025, 54(8): 283-296.
	Liu Zhongmin, Liu Yang, Hu Wenjin. Mural Restoration via Joint Gated Attention and Residual Dense Transformer[J]. Infrared and Laser Engineering, 2025, 54(8): 283-296.
[39]	吴帅. 基于时间协同的反舰导弹攻击战术研究[J]. 舰船电子工程, 2025, 45(6): 31-35.
	Wu Shuai. Research on Anti-ship Missile Attack Tactics Based on Time Coordination[J]. Ship Electronic Engineering, 2025, 45(6): 31-35.

指标	MDA-Net	Baseline-CNN	Baseline-MLP
MacroF1	0.783 2	0.731 5	0.720 8
对抗鲁棒性	0.651 7	0.550 3	0.532 6
时间效能分数	0.982 4	0.954 7	0.991 2
模态互补性	0.821 5	0.602 8	0.551 3
OECI	0.768 9	0.674 3	0.652 7