基于全域火力场的超视距空战威胁预测及动态逃逸方法

李乐言; 杨任农; 郭安新; 宋祺; 左家亮

doi:10.7527/S1000-6893.2025.32205

航空学报 >

0 1 - 0

DOI: https://doi.org/10.7527/S1000-6893.2025.32205

基于全域火力场的超视距空战威胁预测及动态逃逸方法

李乐言 ,
杨任农 ,
郭安新 ,
宋祺 ,
左家亮

展开

1. 空军工程大学空管领航学院
2. 空军工程大学

收稿日期: 2025-05-07

修回日期: 2025-06-30

网络出版日期: 2025-07-03

收起

Beyond Visual Range Air Combat Threat Prediction and Dynamic Evasion Method Based on All-Domain Fire Field Theory

LI Le-Yan ,
YANG Ren-Nong ,
GUO An-Xin ,
SONG Qi ,
ZUO Jia-Liang

Expand

Received date: 2025-05-07

Revised date: 2025-06-30

Online published: 2025-07-03

Fold

摘要

针对空中态势认知中的超视距空战威胁预测问题，提出了一种基于全域火力场的超视距空战威胁预测及动态逃逸方法。首先提出了基于矢量场理论的全域火力场建模方法，定义了单机全域火力场、联合全域火力场及其逃逸场的概念和模型；然后提出了基于多模态残差融合网络（Multi-modal Residual Fusion Network，MRFNet）的火力场实时解算方法，使用“离线训练-在线推理”的深度学习范式解决了传统蒙特卡洛解算方法的计算瓶颈和离散采样畸变问题；同时引入基于向量自回归模型（Vector Autoregressive Model，VAR）的短时航迹预测算法，实时预测敌我多变量飞行状态。所提出的超视距空战威胁预测及动态逃逸方法能够实时解算复杂分布式作战场景下的全局及局部威胁情况，为我机提供针对性威胁预警及逃逸建议。实验结果表明，基于MRFNet的火力场实时解算方法将单次火力场解算时间由分钟级缩短至毫秒级，拟合误差小于5.00e-4，具备良好的数据平滑和外推泛化能力；基于VAR的短时航迹预测算法的经纬度预测误差小于8.73e-4，优于多种基于深度学习的最先进时序预测方法的结果，在雷情探测具有强位置偏差干扰的情况相对误差损失小于22%。综合仿真分析结果，本文提出的方法符合实际空战场景中飞行员的认知逻辑，能够适应复杂分布式作战场景，具有高容错度、强鲁棒性、低时延的特点，有较好的实用价值和现实意义。

关键词： 全域火力场; 态势认知; 超视距空战; 威胁预测; 动态逃逸; 深度学习

本文引用格式

李乐言 , 杨任农 , 郭安新 , 宋祺 , 左家亮 . 基于全域火力场的超视距空战威胁预测及动态逃逸方法[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2025.32205

Abstract

To address the threat prediction issue in beyond-visual-range air combat situational awareness, a global fire field-based threat prediction and dynamic evasion methodology is proposed. Firstly, a vector field theory-driven all-domain fire field modeling framework is established, formally defining the concepts and mathematical models of single-aircraft all-domain fire field, joint all-domain fire field, and their corresponding evasion fields. Subsequently, a real-time fire field computation method based on Multi-modal Residual Fusion Network (MRFNet) is developed, which resolves the computational bottlenecks and discrete field distortion issues inherent in traditional Monte Carlo approaches through an "offline training-online inference" deep learning par-adigm. Concurrently, a short-term trajectory prediction algorithm employing a Vector Autoregressive Model is introduced to enable real-time forecasting of multivariate flight states for both adversarial and friendly aircraft. The proposed methodology enables real-time computation of global and local threat assessments in complex distributed combat scenarios, providing targeted threat warnings and evasion recommendations. Experimental results demonstrate that the MRFNet-based approach reduces sin-gle fire field computation time from minute-level to millisecond-level while maintaining fitting errors below 5.00e-4, exhibiting excellent data smoothing and extrapolation generalization capabilities. The VAR-based trajectory prediction achieves longi-tude/latitude errors below 8.73e-4, outperforming various state-of-the-art deep learning-based time series prediction methods, with relative error losses remaining under 22% under strong positional deviation interference in threat detection. Comprehensive simulation analyses confirm that the proposed methodology aligns with pilots' cognitive logic in real combat scenarios, demon-strating high fault tolerance, strong robustness, and low latency characteristics. This work shows significant practical value and operational relevance for adapting to complex distributed combat environments.

Key words： all-domain fire field; situational awareness; beyond-visual-range air combat; threat prediction; dynamic evasion; deep learning

参考文献

[1]丁鹏, 宋亚飞.代价敏感的空中目标意图识别方法[J].航空学报, 2023, 44(24):328551-328551 [2]DING P, SONG Y F.A cost-sensitive method for aerial target intention recognition[J].Acta Aeronautica et As-tronautica Sinica, 2023, 44(24):328551-328551 [3]RUSSELL S, ABDELZAHER T.The internet of battle-field things: the next generation of command, control, communications and intelligence (C3I) decision-making [C]. MILCOM 2018-2018 IEEE Military Communications Conference (MILCOM), 2018. [4]吴傲, 杨任农, 梁晓龙, 等.基于信息素决策的无人机集群协同搜索算法[J].北京航空航天大学学报, 2021, 47(04):814-827 [5]WU A, YANG R N, LIANG X L, et al.Cooperative search algorithm based on pheromone decision for UAV swarm[J].Journal of Beijing University of Aero-nautics and Astronautics, 2021, 47(04):814-827 [6]何友, 刘瑜, 李耀文, 等.多源信息融合发展及展望[J].航空学报, 2025, 46(6):531672-531672 [7]HE Y, LIU Y, LI Y W, et al.Development and pro-spects of multisource information fusion[J].Acta Aero-nautica et Astronautica Sinica, 2025, 46(6):531672-531672 [8]侯岳奇, 梁晓龙, 何吕龙, 等.未知环境下无人机集群协同区域搜索算法[J].北京航空航天大学学报, 2019, 45(02):347-356 [9]HOU Y Q, LIANG X L, HE L L, et al.Cooperative ar-ea search algorithm for UAV swarm in unknown envi-ronment[J].Journal of Beijing University of Aero-nautics and Astronautics, 2019, 45(02):347-356 [10]COSTA A N, COSTA P C G.Simulation-based air mission evaluation with Bayesian threat assessment for opposing forces[M]. Cham: Springer International Pub-lishing, 2017: 281–295. [11]YIN Y, ZHANG R, SU Q.Threat assessment of aerial targets based on improved GRA-TOPSIS method and three-way decisions[J].Mathematical Biosciences and Engineering, 2023, 20(7):13250-13266 [12]王宇航, 董宝良, 公超, 等.基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, (12): 100-104+111.[J].计算机与现代化, 2023, 12:100-104 [13]WANG Y H, DONG B L, GONG C, et al.Dynamic threat assessment of air swarm targets based on intent recognition[J]. Computer and Modernization, 2023, (12): 100-104+111 (in Chinese). [14]和烨龙, 张鹏飞, 赵永娟, 等.基于和组合赋权的法蜂群威胁评估研究[J].火炮发射与控制学报, 2024, 45(01):28-35 [15]HE Y L, ZHANG P F, ZHAO Y J, et al.TOPSIS meth-od based on CRITIC and AHP combination weighting research on bee colony threat assessment[J].Journal of Gun Launch＆Control, 2024, 45(01):28-35 [16]唐磊, 冀春雷, 韩鹏.四代机编队超视距作战效能评估模型研究[J].指挥控制与仿真, 2021, 43(03):49-52 [17]TANG L, JI C L, HAN P.Research on evaluation model of beyond-visual-range combat effectiveness of fourth-generation aircraft formation[J].Command Con-trol＆Simulation, 2021, 43(03):49-52 [18]谢岚风, 陈军, 焦璐, 等.未来空战全域火力场研究[J].航空学报, 2024, 45(5):529699-529699 [19]XIE L F, CHEN J, JIAO L, et al.All-domain fire field in future air combat[J].Acta Aeronautica et Astronauti-ca Sinica, 2024, 45(5):529699-529699 [20]曹玥瑶, 薛涛, 何闪闪, 等.超视距空战全域火力场计算及态势评估和辅助决策应用[J/OL]. 北京航空航天大学学报, （2025-04-29）[2025-04-29]. https://doi.org/10.13700/j.bh.1001-5965.2024.0399. [21]CAO Y Y, XUE T, HE S S, et al.Calculation of Be-yond Visual Range Air Combat All-Domain Fire Field and Application of Situation Threat Assessment and Assisted Decision Making[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, （2025-04-29）[2025-04-29]. https://doi.org/10.13700/j.bh.1001-5965.2024.0399 (in Chinese). [22]闫孟达, 杨任农, 左家亮, 等.基于深度学习的空空导弹多类攻击区实时解算[J].兵工学报, 2020, 41(12):2466-2477 [23]YAN M D, YANG R N, ZUO J L, et al.Real-time computing of air-to-air missile multiple capture zones based on deep learning[J].Acta Armamentarii, 2020, 41(12):2466-2477 [24]胡东愿, 杨任农, 闫孟达, 等.基于自编码网络的导弹攻击区实时计算方法[J].航空学报, 2020, 41(04):231-247 [25]HU D Y, YANG R N, YAN M D, et al.Real-time cal-culation of missile launch envelope based on auto-encoder network[J].Acta Aeronautica et Astronaotica Sinica, 2020, 41(04):231-247 [26] 游航航, 宋帅, 高阳阳, 等.超视距空战中指挥引导效能的发挥[J]. 飞航导弹, 2019, (11): 70-72. [27]YOU H H, SONG S, GAO Y Y, et al.The performance of command and guidance in over-the-horizon air com-bat[J]. Aerospace Technology, 2019, (11): 70-72 (in Chinese). [28]夏博远.马赛克战中面向杀伤网的作战环推荐方法研究[D]. 国防科技大学, 2021. [29]XIA B Y.A study of operation loop recommendation methods for kill web in the mosaic war[D]. National University of Technology, 2021 (in Chinese). [30]张健, 罗鑫悦, 黎宗孝, 等.基于动态贝叶斯网络的无人机航迹模型研究[J].中国安全生产科学技术, 2023, 19(11):188-193 [31]ZHANG J, LUO X Y, LI Z X, et al.Research on UAV track model based on dynamic Bayesian network[J].Journal of Safety and Technology, 2023, 19(11):188-193 [32]石庆研, 岳聚财, 韩萍, 等.基于-模型的短期航班飞行轨迹预测[J].信号处理, 2019, 35(12):2000-2009 [33]SHI Q Y, YUE J C, HAN P, et al.Short-term flight trajectory prediction based on LSTM-ARIMA model[J].Journal of Signal Processing, 2019, 35(12):2000-2009 [34]HAN X, TIAN C.Vessel track prediction based on fractional gradient recurrent neural network with ma-neuvering behavior identification[J].Scientific Pro-gramming, 2021, 2021(2021):5526082- [35]ZHENG Y, LV X, QIAN L, LIU X.An optimal BP neural network track prediction method based on a GA–ACO hybrid algorithm[J].Journal of Marine Sci-ence and Engineering, 2022, 10(10):1399- [36] VASWANI A, SHAZEER N, PARMAR N, et al.Atten-tion is all you need[J]. arXiv, 2017. DOI: 10.48550/arXiv.1706.03762. [37]ZHOU H, ZHANG S, PENG J, et al.Informer: beyond efficient Transformer for long sequence time-series forecasting[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12):11106-11115 [38]SEPP H, JURGEN S.Long short-term memory[J].Neural Computation, 1997, 9(8):1735-1780 [39]LI L Y, YANG R N, LI H Y, et al.Unsupervised con-trastive learning for automatic grouping of aerial swarms[J].IEEE Transactions on Vehicular Technology, 2024, 73(5):6249-6258

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献