基于气动力加速度估计的高超声速滑翔飞行器智能轨迹预测

doi:10.12382/bgxb.2025.0035

摘要/Abstract

摘要：

临近空间高超声速滑翔飞行器(Hypersonic Gliding Vehicle,HGV)具有高速、高机动特性以及超强的突防能力,对现有防御系统造成严重威胁。针对临近空间高机动目标拦截任务中跟踪预测难的问题,提出一种基于气动力加速度估计的HGV智能轨迹预测方法。根据HGV目标运动模型,分析其机动模式和气动力变化规律,选定气动升力加速度、气动阻力加速度和倾侧角控制量3个参数作为轨迹预测参数,替代目标运动模型中的未知项。建立基于气动加速度估计的动力学跟踪模型,利用雷达量测数据和无迹卡尔曼滤波实现预测参数的实时跟踪估计,并以此为输入构建长短时记忆(Long Short-Term Memory,LSTM)网络训练模型,对预测参数的变化规律与时序关系进行在线学习。利用训练完备的LSTM预测网络迭代预测目标未来时刻的气动加速度,结合运动方程数值积分外推,实现目标轨迹在线预测。数值仿真结果表明,新方法能有效预测非合作HGV目标轨迹,预测精度高、稳定性好。

关键词: 高超声速滑翔飞行器, 气动加速度估计, 跟踪滤波, 长短时记忆网络, 轨迹预测

Abstract:

The near-space hypersonic gliding vehicle (HGV) poses a significant threat to existing defense systems due to its ultra-high velocity,extreme maneuverability,and superior penetration capabilities.To address the challenges in tracking and predicting HGV trajectories during interception,this paper presents an intelligent trajectory prediction method based on aerodynamic acceleration estimation.The maneuver patterns and aerodynamic variation laws of HGV are systematically analyzed according to the HGV motion model.On this basis,three critical parameters,i.e.,aerodynamic lift acceleration,drag acceleration and bank angle control,are identified as trajectory prediction variables for replacing the unknown terms in the HGV motion model.A dynamics tracking model based on aerodynamic acceleration estimation is developed to use the radar measurement data and the unscented Kalman filter (UKF) for real-time tracking and estimation of these parameters.These estimated parameters are then used as inputs to train a long short-term memory (LSTM) network,which captures the temporal relationships and variation patterns in the prediction parameters.The trained LSTM network is used to iteratively forecasts future aerodynamic accelerations,which are integrated with the numerical solutions of motion equations to extrapolate HGV trajectories.Numerical simulations confirm that the proposed method achieves high prediction accuracy and robust stability in predicting the trajectories of non-cooperative HGVs.

Key words: hypersonic gliding vehicle, aerodynamic acceleration estimation, tracking filter, LSTM network, trajectory prediction

中图分类号:

TP13

余明骏, 张佳梁, 沈海东, 刘燕斌, 陈金宝. 基于气动力加速度估计的高超声速滑翔飞行器智能轨迹预测[J]. 兵工学报, 2025, 46(6): 240035-.

YU Mingjun, ZHANG Jialiang, SHEN Haidong, LIU Yanbin, CHEN Jinbao. Intelligent Hypersonic Gliding Vehicle Trajectory Prediction Based on Aerodynamic Acceleration Estimation[J]. Acta Armamentarii, 2025, 46(6): 240035-.

图/表 32

图1 不同攻角条件下的气动力加速度

Fig.1 Aerodynamic accelerations at different angles of attack

图2 雷达量测模型

Fig.2 Radar observation model

图3 基于LSTM参数辨识的轨迹预测方法总体方案

Fig.3 Overall scheme of trajectory prediction method based on LSTM parameter identification

图4 基于LSTM预测网络的轨迹递归预测方法

Fig.4 LSTM network-based trajectory recursive prediction

图5 数据分段过程

Fig.5 Data segmentation procedure

图6 LSTM网络结构

Fig.6 LSTM network structure

图7 仿真场景

Fig.7 Simulation scene

表1 神经元节点数设置

Table 1 Neuron node number Settings

网络层	神经元个数
LSTM层1	64
LSTM层2	128
输入层1	64
输入层2	3

表 2 网络训练超参数设置

Table 2 Network training hyperparameter settings

参数	取值
最大训练迭代次数	100
最小批次	128
初始学习率	0.005
学习率下降因子	0.2
正则化系数	0.1
优化器	Adam

图8 LSTM网络训练过程中的损失

Fig.8 Loss during training of LSTM network

图9 气动阻力加速度跟踪结果

Fig.9 Tracking results of aerodynamic drag acceleration

图10 气动升力加速度跟踪结果

Fig.10 Tracking results of aerodynamic lift acceleration

图11 倾侧角正弦量跟踪结果

Fig.11 Tracking results of sinusoidal quantity of bank angle

图12 目标航迹角估计结果

Fig.12 Estimated result of target flight-path angle

图13 目标航向角估计结果

Fig.13 Estimated result of target heading angle

图14 目标速度估计结果

Fig.14 Estimated result of target speed

图15 目标空间位置估计结果

Fig.15 Estimated result of target spatial location

图16 气动阻力加速度预测结果

Fig.16 Predicted results of aerodynamic drag acceleration

图17 气动升力加速度预测结果

Fig.17 Predicted result of aerodynamic lift acceleration

图18 倾侧角正弦量预测结果

Fig.18 Predicted results of sinusoidal quantity of bank angle

图19 目标航迹角预测结果

Fig.19 Predicted result of target flight-path angle

图20 目标航向角预测结果

Fig.20 Predicted result of target heading angle

图21 目标速度预测结果

Fig.21 Predicted result of target speed

图22 目标轨迹经度随时间变化

Fig.22 Variation of target trajectory longitude over time

图23 目标轨迹纬度随时间变化

Fig.23 Variation of target trajectory latitude over time

图24 目标轨迹高度随时间变化

Fig.24 Variation of target trajectory height over time

图25 不同预报方法结果对比

Fig.25 Result comparison of different predicting methods

图26 蒙特卡洛仿真结果

Fig.26 Results of Monte Carlo simulations

图27 蒙特卡洛横向平面仿真结果

Fig.27 Monte Carlo simulation results of horizontal plane

图28 蒙特卡洛仿真对应的RMSE

Fig.28 RMSEs corresponding to Monte Carlo simulations

表3 3种方法平均在线预测耗时

Table 3 Average online prediction time for three methods

方法	在线训练耗时/s	在线预测耗时/s
文献[29]方法		0.0089
文献[30]方法		0.2117
本文方法	13.6	0.2932

图29 跟踪-决策-预测时间轴

Fig.29 Tracking-decision-Pprediction timeline

参考文献 32

[1]	LI F, XIONG J J, LAN X H, et al. Hypersonic vehicle trajectory prediction algorithm based on Hough transform[J]. Chinese Journal of Electronics, 2021, 30(5):918-930.
[2]	MAEDER U, MORARI M, BAUMGARTNER T I. Trajectory prediction for light aircraft[J]. Journal of Guidance,Control,and Dynamics, 2011, 34(4):1112-1119.
[3]	邵雷, 雷虎民, 赵锦. 临近空间高超声速飞行器轨迹预测方法研究进展[J] 航空兵器, 2021, 28(2):34-39.
	SHAO L, LEI H M, ZHAO J. Research progress in trajectory prediction for near space hypersonic vehicle[J]. Aero Weaponry, 2021, 28(2):34-39. (in Chinese)
[4]	张凯, 熊家军, 李凡, 等. 基于意图推断的高超声速滑翔目标贝叶斯轨迹预测[J]. 宇航学报, 2018, 39(11):1258-1265.
	ZHANG K, XIONG J J, LI F, et al. Bayesian trajectory prediction for a hypersonic gliding reentry vehicle based on intent inference[J]. Journal of Astronautics, 2018, 39(11):1258-1265. (in Chinese)
[5]	HU Y D, GAO C S, LI J L, et al. Novel trajectory prediction algorithms for hypersonic gliding vehicles based on maneuver mode on-line identification and intent inference[J]. Measurement Science and Technology, 2021, 32(11):115012.
[6]	韩宇辰, 王松艳, 权申明, 等. 基于贝叶斯推断的高超声速滑翔目标轨迹预测方法[J]. 控制与决策, 2024, 39(11):3736-3744.
	HAN Y C, WANG S Y, QUAN S M, et al. A method of predicting for the trajectory of hypersonic gliding targets based on Bayesian inference[J]. Control and Decision, 2024, 39(11):3736-3744. (in Chinese)
[7]	李佳丽, 郭杰, 唐胜景. 面向高超声速滑翔目标的多模型多意图融合轨迹预测[J]. 宇航学报, 2024, 45(2):167-180.
	LI J L, GUO J, TANG S J. Trajectory prediction based on multi-model and multi-intent fusion for hypersonic gliding targets[J]. Journal of Astronautics, 2024, 45(2):167-180. (in Chinese)
[8]	韩春耀, 熊家军, 张凯, 等. 高超声速飞行器分解集成轨迹预测算法[J]. 系统工程与电子技术, 2018, 40(1):151-158.
	HAN C Y, XIONG J J, ZHANG K, et al. Decomposition ensemble trajectory prediction algorithm for hypersonic vehicle[J]. Systems Engineering and Electronics, 2018, 40(1):151-158. (in Chinese) doi: 10.3969/j.issn.1001-506X.2018.01.22
[9]	寇英信, 奚之飞, 徐安, 等. 基于改进核极限学习机和集成学习理论的目标机动轨迹预测[J]. 国防科技大学学报, 2021, 43(5):23-35.
	KOU Y X, XI Z F, XU A, et al. Maneuver trajectory prediction of target based on improved KELM and ensemble learning theory[J]. Journal of National University of Defense Technology, 2021, 43(5):23-35. (in Chinese)
[10]	胡星志, 王旭, 江雄, 等. 基于高斯过程回归的高超声速飞行器不确定轨迹预测[J]. 空天技术, 2022(4):49-61.
	HU X Z, WANG X, JIANG X, et al. Uncertain trajectory prediction of hypersonic flight vehicles based on Gaussian process regression[J]. Aerospace Technology, 2022(4):49-61. (in Chinese)
[11]	张洪波, 黄景帅, 李广华, 等. 典型控制规律滑翔飞行器的轨迹预测方法[J]. 现代防御技术, 2017, 45(4):112-118.
	ZHANG H B, HUANG J S, LI G H, et al. Trajectory prediction of glide vehicle based on typical control law[J]. Modern Defence Technology, 2017, 45(4):112-118. (in Chinese)
[12]	魏喜庆, 顾龙飞, 李瑞康. 基于Singer模型的高超声速飞行器轨迹跟踪与预测[J]. 航天控制, 2017, 35(4):62-72.
	WEI X Q, GU L F, LI R K. Trajectory tracking and prediction of hypersonic vehicle based on Singer model[J]. Aerospace Control, 2017, 35(4):62-72. (in Chinese)
[13]	翟岱亮, 雷虎民, 李炯, 等. 基于自适应IMM的高超声速飞行器轨迹预测[J]. 航空学报, 2016, 37(11):3466-3475. doi: 10.7527/S1000-6893.2016.0044
	ZHAI D L, LEI H M, LI J, et al. Trajeclory prediction of hypersonic vehicle based on adaplive IMM[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(11):3466-3475. (in Chinese)
[14]	NAIK J S, KASIVISWANATH N, AHAMED K I, et al. A survey on traffic flow prediction with deep learning algorithms on big data[J]. International Journal of Recent Technology and Engineering, 2019, 7(5C):28-33.
[15]	吉瑞萍, 张程祎, 梁彦, 等. 基于LSTM的弹道导弹主动段轨迹预报[J]. 系统工程与电子技术, 2022, 44(6):1968-1976. doi: 10.12305/j.issn.1001-506X.2022.06.24
	JI R P, ZHANG C Y, LIANG Y, et al. Trajectory prediction of boost-phase ballistic missile based on LSTM[J]. Systems Engineering and Electronics, 2022, 44(6):1968-1976. (in Chinese) doi: 10.12305/j.issn.1001-506X.2022.06.24
[16]	杨春伟, 刘炳琪, 王继平, 等. 基于注意力机制的高超声速飞行器LSTM智能轨迹预测[J]. 兵工学报, 2022, 43(增刊2):78-86.
	YANG C W, LIU B Q, WANG J P, et al. LSTM intelligent trajectory prediction for hypersonic vehicles based on attention mechanism[J]. Acta Armamentarii, 2022, 43(S2):78-86. (in Chinese) doi: 10.12382/bgxb.2022.B002
[17]	SUN L H, YANG B Q, JIE M. Trajectory prediction in pipeline form for intercepting hypersonic gliding vehicles based on LSTM[J]. Chinese Journal of Aeronautics, 2023, 36(5):421-433.
[18]	张堃, 杜睿怡, 时昊天, 等. 基于Mogrifier-BiGRU的飞行器轨迹预测[J]. 兵工学报, 2024, 45(2):373-384. doi: 10.12382/bgxb.2022.0750
	ZHANG K, DU R Y, SHI H T, et al. Prediction of aircraft trajectory based on Mogrifier-BiGRU[J]. Acta Armamentarii, 2024, 45(2):373-384. (in Chinese) doi: 10.12382/bgxb.2022.0750
[19]	李强. 高超声速滑翔飞行器再入制导控制技术研究[D]. 北京: 北京理工大学, 2015.
	LI Q. Study on reentry guidance and control method for hypersonic glide vehicle[D]. Beijing: Beijing Institute of Technology, 2015. (in Chinese)
[20]	张君彪, 熊家军, 兰旭辉, 等. 一种高超声速滑翔飞行器轨迹智能预测方法[J]. 宇航学报, 2022, 43(4):413-422.
	ZHANG J B, XIONG J J, LAN X H, et al. An intelligent prediction method of hypersonic glide vehicle trajectory[J]. Journal of Astronautics, 2022, 43(4):413-422. (in Chinese)
[21]	朱建文. 助推-滑翔飞行器自适应全程制导方法研究[D]. 长沙: 国防科学技术大学, 2016.
	ZHU J W. Research on adaptive all-course guidance for boost-glide vehicles[D]. Changsha: National University of Defense Technology, 2016. (in Chinese)
[22]	兰旭辉, 熊家军, 张君彪, 等. 临近空间高超声速飞行器轨迹预测技术[M]. 武汉: 华中科技大学出版社, 2022.
	LAN X H, XIONG J J, ZHANG J B, et al. Trajectory prediction technology of near space hypersonic vehicle[M]. Wuhan: Huazhong University of Science and Technology Press, 2022. (in Chinese)
[23]	程云鹏. 高超声速滑翔飞行器轨迹估计和预报方法研究[D]. 西安: 西北工业大学, 2021.
	CHENG Y P. Research on trajectory estimation and prediction of hypersonic gliding vehicles[D]. Xi’an: Northwestern Polytechnical University, 2021. (in Chinese)
[24]	黄景帅. 高超声速滑翔目标跟踪与拦截制导方法研究[D]. 长沙: 国防科学技术大学, 2020.
	HUANG J S. Tracking and intercept guidance methods against hypersonic glide targets[D]. Changsha: National University of Defense Technology, 2020. (in Chinese)
[25]	李佳兴, 袁利, 张聪. 天基单视线测量目标轨道可观性分析及确定方法[J]. 航空学报, 2025, 46(3):629484.
	LI J X, YUAN L, ZHANG C. Observability analysis and orbit determination of targets using spacebased single line-of-sight measurement[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3):629484. (in Chinese)
[26]	HU Y P, SHARF I, CHEN L. Distributed orbit determination and observability analysis for satellite constellations with angles-only measurements[J]. Automatica, 2021, 129:109626.
[27]	KINGMA D P. Adam:a method for stochastic optimization:arXiv.1412.6980[R/OL]. Ithaca,NY, US: Cornell University, 2014(2014-12-22). https://arxiv.org/abs/1412.6980.
[28]	李广华. 高超声速滑翔飞行器运动特性分析及弹道跟踪预报方法研究[D]. 长沙: 国防科学技术大学, 2016.
	LI G H. Motion characteristics analysis and trajectory prediction for hypersonic glide vehicles[D]. Changsha: National University of Defense Technology, 2016. (in Chinese)
[29]	李世杰, 雷虎民, 周池军, 等. 基于控制变量估计的高超声速再入滑翔目标轨迹预测算法[J]. 系统工程与电子技术, 2020, 42(10):2320-2327. doi: 10.3969/j.issn.1001-506X.2020.10.21
	LI S J, LEI H M, ZHOU C J, et al. Trajectory prediction algorithm for hypersonic reentry gliding target based on control variables estimation[J]. Systems Engineering and Electronics, 2020, 42(10):2320-2327. (in Chinese) doi: 10.3969/j.issn.1001-506X.2020.10.21
[30]	苏雨, 张龙政腾, 赵国宏, 等. 基于GRU-KAN的高速飞行器轨迹预测方法[J]. 航空兵器, 2024, 31(6):44-49.
	SU Y, ZHANG L Z T, ZHAO G H, et al. Long term trajectory prediction of hypersonic aircraft based on GRU-KAN[J]. Aero Weaponry, 2024, 31(6):44-49. (in Chinese)
[31]	郑建成, 谭贤四, 曲智国, 等. 高超声速滑翔飞行器特性分析与防御发展趋势[J]. 飞航导弹, 2021(11):52-57,70.
	ZHENG J C, TAN X S, QU Z G, et al. Characterization of hypersonic gliding vehicles and development trend of defense[J]. Aerodynamic Missile Journal, 2021(11):52-57,70. (in Chinese)
[32]	赵良玉, 雍恩米, 王波兰. 反临近空间高超声速飞行器若干研究进展[J]. 宇航学报, 2020, 41(10):1239-1250.
	ZHAO L Y, YONG E M, WANG B L. Some achievements on interception of near space hypersonic vehicles[J]. Journal of Astronautics, 2020, 41(10):1239-1250. (in Chinese)