基于卷积神经网络的无人作战飞机飞行轨迹实时预测

doi:10.3969/j.issn.1000-1093.2020.09.022

摘要/Abstract

摘要： 飞行轨迹预测是空战技术的一部分，预测方结合轨迹预测结果可以选择出更有预见性的机动。为快速、准确地获得无人作战飞机在未来时刻的位置，提出了基于卷积神经网络的飞行轨迹预测方法。原始动力学模型不能正确仿真滚转角有偏差的筋斗机动，采取限制角速度的方式对该模型进行改进；使用改进后的模型在不同条件下进行飞行仿真，得到大量轨迹样本；训练并测试具有不同层数和卷积核数的网络，从中找出预测误差最小的网络；对比卷积神经网络与长短时记忆网络、循环神经网络、全连接网络的运算速度和误差，结果表明：卷积神经网络预测方法在没有增加运算用时情况下，0.25 s后的平均预测误差在x轴方向约为4.2 m，y轴方向约为8.0 m，z轴方向约为19.5 m，且误差均小于其他3种方法。

关键词: 无人作战飞机, 飞行轨迹预测, 卷积神经网络, 循环神经网络, 动力学模型, 飞行仿真

Abstract: Trajectory prediction is part of air combat technology，and the predictors can select a more predictable maneuvering considerion of trajectory prediction results. A convolution neural network predicting method is proposed to obtain the position of unmanned combat aerial vehicle in a future time quickly and accurately. An improved model for limiting the angular velocity is presented since the original dynamic model can not correctly simulate the somersault maneuvering with roll angle deviation. The improved model is used for flight simulation under different conditions，and a large number of trajectory samples are obtained. The convolution neural networks with different layer number and convolution kernel number is trained and tested，and the network with the smallest prediction error is selected. Operational speed and error of the proposed method are compared with those of long short term memory neural network，recurrent neural network and fully connected neural network. The results show that the average prediction error of the proposed method is about 4.2 m on x axis，8.0 m on y axis and 19.5 m on z axis after 0.25 s without increasing operational time，and the errors are all smaller than those of the other methods.

Key words: unmamedcombataerialvehicle, flighttrajectoryprediction, convolutionalneuralnetwork, recurrentneuralnetwork, dynamicsmodel, flightsimulation

中图分类号:

E844

张宏鹏，黄长强，唐上钦，轩永波. 基于卷积神经网络的无人作战飞机飞行轨迹实时预测[J]. 兵工学报, 2020, 41(9): 1894-1903.

ZHANG Hongpeng， HUANG Changqiang， TANG Shangqin， XUAN Yongbo. CNN-based Real-time Prediction Method of Flight Trajectory of Unmanned Combat Aerial Vehicle[J]. Acta Armamentarii, 2020, 41(9): 1894-1903.

参考文献

[1] HUANG C Q，DONG K S，HUANG H Q，et al.Autonomous air combat maneuver decision using Bayesian inference and moving horizon optimization[J].Journal of Systems Engineering and Electronics，2018，29(1):86-97.
[2] 孙楚，赵辉，王渊，等.基于强化学习的无人机自主机动决策方法[J].火力与指挥控制，2019，44(4):142-149.
SUN C，ZHAO H，WANG Y，et al. UCAV autonomic maneuver decision-making method based on reinforcement learning[J].Fire Control and Command Control，2019，44(4):142-149.(in Chinese)
[3] 杜海文，崔明朗，韩统，等.基于多目标优化与强化学习的空战机动决策[J].北京航空航天大学学报，2018，44(11):2247-2256.
DU H W，CUI M L，HAN T，et al.Maneuvering decision in air combat based on multi-objective optimization and reinforcement learning[J]. Journal of Beijing University of Aeronautics and Astronautics，2018，44(11):2247-2256.(in Chinese)
[4] 李世豪，丁勇，高振龙.基于直觉模糊博弈的无人机空战机动决策[J].系统工程与电子技术，2019，41(5):1063-1070.
LI S H，DING Y，GAO Z L.UAV air combat maneuvering decision based on intuitionistic fuzzy game theory[J]. Systems Engineering and Electronics，2019，41(5):1063-1070.(in Chinese)
[5] 张涛，郭基联，徐西蒙，等.基于Elman神经网络的战斗机空战轨迹预测[J].飞行力学，2018，36(5):86-91.
ZHANG T，GUO J L，XU X M，et al. Air combat trajectory prediction of a fighter based on Elman neural network[J].Flight Dynamics， 2018，36(5):86-91.(in Chinese)
［6］王新，杨任农，左家亮，等.基于HPSO-TPFENN的目标机轨迹预测[J].西北工业大学学报，2019，37(3):613-620.
WANG X，YANG R N，ZUO J L，et al. Trajectory prediction of target aircraft based on HPSO-TPFENN neural network[J].Journal of Northwestern Polytechnical University，2019，37(3):613-620.(in Chinese)
［7］钱夔，周颖，杨柳静，等.基于BP神经网络的空中目标航迹预测模型[J].指挥信息系统与技术，2017，8(3):54-58.
QIAN K，ZHOU Y，YANG L J，et al. Aircraft target track prediction model based on BP neural network[J].Command Information System and Technology，2017，8(3):54-58.(in Chinese)
[8] LYMPEROPOULOS I，LYGEROS J.Adaptive aircraft trajectory prediction using particle filters[C]∥Proceedings of Guidance，Navigation and Control Conference and Exhibit. Honolulu, HI，US:AIAA，2008:1-16.
[9] LEFFERTS E J，MARKLEY F L，MALCOLM D S. Kalman filtering for spacecraft attitude estimation[J].Journal of Guidance Control and Dynamics，1982，5(5):417-429.
[10] QIAO S J，SHEN D Y，WANG X T，et al.A self-adaptive parameter selection trajectory prediction approach via hidden Markov models[J].IEEE Transactions on Intelligent Transportation Systems，2015，16(1):284-296.
[11] AKCAL M U，URE N K，YANG C G，et al. Predictive missile guidance with online trajectory learning[J]. Defence Science Journal，2017，67(3):332-338.
［12］ WANG Q Y，ZHANG Z L，WANG Z Y，et al. The trajectory prediction of spacecraft by grey method[J].Measurement Science and Technology，2016，27(8):085011.
［13］ ALAHI A，GOEL K，RAMANATHAN V，et al. Social LSTM: human trajectory prediction in crowded spaces[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway，NJ, US:IEEE，2016:961-971.
[14] NIKHIL N，MORRIS B T.Convolutional neural network for trajectory prediction[C]∥Proceedings of ECCV 2018 Workshops. Switzerland: Springer，2019:186-196.
[15] TIAN X，JEFFREY C.Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties[J].Physical Review Letters，2018，120(14):1-6.
[16] WILLIAMS P. Three-dimensional aircraft terrain-following via real-time optimal control[J]. Journal of Guidance，Control, and Dynamics， 2007,30 (4) : 1201-1205.
[17] 古德费洛.深度学习[M].北京：人民邮电出版社，2017:201-226.
GOODFELLOW. Deep learning[M].Beijing: People's Post and Telecommunications Press，2017:201-226.(in Chinese)
[18] HUBEL D H，WIESEL T N.Recepective fields，binocular interaction，and functional architecture in the cat's visual cortex[J]. Journal of Physiology，1962，160: 106-154.
[19] 毛景慧.基于LSTM深度神经网络的股市时间序列预测精度的影响因素研究[D].广州:暨南大学，2017:25-26.
MAO J H.Research on influencing factors of stock market time series prediction accuracy based on LSTM deep neural network[D]. Guangzhou:Jinan University，2017:25-26.(in Chinese)
[20] HORNIK K，STINCHCOMBE M，WHITE H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks[J].Neural Networks，1990，3:551-560.
[21] DUCHI J, HAZAN E, SINGER Y. Adaptive subgradient methods for online learning and stochastic optimization[J].Journal of Machine Learning Research，2011，12(7):2121-2159.
[22] 国海峰，侯满义，张庆杰，等.基于统计学原理的无人作战飞机鲁棒机动决策[J].兵工学报，2017，38(1):160-167.
GUO H F，HOU M Y，ZHANG Q J，et al. UCAV robust maneuver decision based on statistics principle[J]. Acta Armamentarii，2017，38(1):160-167.(in Chinese)

[1]	袁航，罗迎，李开明，陈怡君，张群. 基于涡旋电磁波雷达的人体目标步态精细识别[J]. 兵工学报, 2022, 43(5): 1167-1174.
[2]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[3]	李春明, 吴维, 郭智蔷, 苑士华, 陈思. 履带车辆纵向与垂向耦合动力学模型及功率特性[J]. 兵工学报, 2021, 42(3): 449-458.
[4]	马月红，孔梦瑶. 基于改进快速区域卷积网络的目标检测轻量化算法[J]. 兵工学报, 2021, 42(12): 2664-2674.
[5]	叶建川，王江，梁熠，宋韬，吴则良，徐超. 四旋翼无人机前飞模态特性[J]. 兵工学报, 2021, 42(11): 2476-2490.
[6]	刘秋，孙晋伟，张华, 胡煦，顾亮. 基于卷积神经网络的路面识别及半主动悬架控制[J]. 兵工学报, 2020, 41(8): 1483-1493.
[7]	张宏鹏，黄长强，轩永波，唐上钦. 基于深度神经网络的无人作战飞机自主空战机动决策[J]. 兵工学报, 2020, 41(8): 1613-1622.
[8]	韩晋阳, 白春华，檀盼龙. 伞降战斗部毁伤试验落点预测方法研究[J]. 兵工学报, 2020, 41(6): 1077-1084.
[9]	呙鹏程，吴礼洋. 融合卷积特征与判别字典学习的低截获概率雷达信号识别[J]. 兵工学报, 2019, 40(9): 1881-1889.
[10]	张青斌，高峰，郭锐，丰志伟，葛健全. 动力翼伞系统拟坐标形式的多体动力学建模[J]. 兵工学报, 2019, 40(9): 1935-1942.
[11]	吴春志，冯辅周，吴守军，陈汤，江鹏程. 一种有效的不均衡样本生成方法及其在行星变速箱故障诊断中的应用[J]. 兵工学报, 2019, 40(7): 1349-1357.
[12]	梁杰，李磊，任君，齐航，周红丽. 基于深度学习的红外图像遮挡干扰检测方法[J]. 兵工学报, 2019, 40(7): 1401-1410.
[13]	姜俊峰，李伟，赵维，周晓军. 船载转塔装置随动系统动力学建模与仿真[J]. 兵工学报, 2019, 40(4): 829-836.
[14]	张玉燕，李永保，温银堂，张芝威. 基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法[J]. 兵工学报, 2019, 40(11): 2329-2335.
[15]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.