一种目标典型航迹形状仿真及多视角识别算法

doi:10.16182/j.issn1004731x.joss.25-0022

摘要/Abstract

摘要：

针对现有航迹仿真手段未能充分考虑目标航迹几何形状特征与运动学特性，提出一种基于运动学规律的目标航迹形状仿真算法。通过集成多种轨迹极坐标方程与曲率方程，结合运动学方程求解飞行器状态参数；引入角度高斯噪声增强轨迹的多样性与真实性，设计一种多视角航迹形状识别算法，采用多层感知机有效融合图像与序列多模态特征，实现对轨迹形状的精确识别。实验结果表明：所提算法能够生成符合物理规律的多样化航迹数据，基于多视角的识别模型较单一视角识别方法具有更高的识别准确率，验证了航迹形状仿真与识别算法的有效性。

关键词: 航迹形状仿真, 轨迹形状识别, 多视角学习, 多模态特征, 深度学习

Abstract:

Current trajectory simulation methods inadequately address geometric shape features and kinematic properties of the target trajectory. To bridge this gap, a target trajectory shape simulation algorithm based on kinematic laws was proposed. The polar coordinate equations and curvature equations of multiple trajectories were integrated. The aircraft state parameters were solved by combining kinematic equations. Angular Gaussian noise was introduced to enhance trajectory diversity and authenticity. Additionally, a multi-perspective trajectory shape recognition algorithm was designed, which could effectively integrate image and sequential multi-modal features by adopting a multilayer perceptron, enabling precise trajectory shape recognition. Experimental results demonstrate that the proposed algorithm can generate diverse trajectory data conforming to physical laws. The multi-perspective recognition models achieve higher accuracy compared to single-perspective recognition models, validating the effectiveness of both trajectory shape simulation and recognition algorithms.

Key words: trajectory shape simulation, trajectory shape recognition, multi-view learning, multi-modal feature, deep learning

中图分类号:

TP391.9

冯雪健,丁晗,童逸琦等 . 一种目标典型航迹形状仿真及多视角识别算法[J]. 系统仿真学报, 2026, 38(3): 725-735.

Feng Xuejian,Ding Han,Tong Yiqi,et al . Simulation and Multi-perspective Recognition Algorithm for Typical Trajectory Shapes[J]. Journal of System Simulation, 2026, 38(3): 725-735.

图/表 10

图1

图2

图3

表1

图4

图5

图6

表2

图7

表3

参考文献 22

[1]	初阳, 刘志, 窦林涛. 面向大尺度战场的飞行机动建模仿真技术[J]. 系统仿真学报, 2021, 33(3): 613-621.
	Chu Yang, Liu Zhi, Dou Lintao. Modeling and Simulation Technology of Flight Maneuver for Large Scale battlefield[J]. Journal of System Simulation, 2021, 33(3): 613-621.
[2]	孙淑光, 程鹏. 基于航迹约束的三维飞行轨迹仿真生成器[J]. 系统仿真学报, 2019, 31(2): 275-282, 293.
	Sun Shuguang, Cheng Peng. 3D Flight Trajectory Simulation Generator Based on Track Constraints[J]. Journal of System Simulation, 2019, 31(2): 275-282, 293.
[3]	唐剑, 张杰勇, 焦志强, 等. 空战场多分支态势仿真生成方法[J]. 指挥信息系统与技术, 2019, 10(3): 11-17.
	Tang Jian, Zhang Jieyong, Jiao Zhiqiang, et al. Multi-branch Situation Simulation Generation Method for Air Battlefield[J]. Command Information System and Technology, 2019, 10(3): 11-17.
[4]	张冬, 杨继国, 尤灵辰, 等. 基于可变自主等级的有人机/无人机控制方法[J]. 无人系统技术, 2023, 6(6): 80-90.
	Zhang Dong, Yang Jiguo, You Lingchen, et al. A Control Method for Manned/Unmanned Aerial Vehicle Formation Based on Variable Autonomy[J]. Unmanned Systems Technology, 2023, 6(6): 80-90.
[5]	Zhao Yijing, Zheng Zheng, Zhang Xiaoyi, et al. Q Learning Algorithm Based UAV Path Learning and Obstacle Avoidence Approach[C]//2017 36th Chinese Control Conference (CCC). Piscataway: IEEE, 2017: 3397-3402.
[6]	张堃, 李珂, 时昊天, 等. 基于深度强化学习的UAV航路自主引导机动控制决策算法[J]. 系统工程与电子技术, 2020, 42(7): 1567-1574.
	Zhang Kun, Li Ke, Shi Haotian, et al. Autonomous Guidance Maneuver Control and Decision-making Algorithm Based on Deep Reinforcement Learning UAV Route[J]. Systems Engineering and Electronics, 2020, 42(7): 1567-1574.
[7]	周攀, 黄江涛, 章胜, 等. 基于深度强化学习的智能空战决策与仿真[J]. 航空学报, 2023, 44(4): 94-107.
	Zhou Pan, Huang Jiangtao, Zhang Sheng, et al. Intelligent Air Combat Decision Making and Simulation Based on Deep Reinforcement Learning[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(4): 94-107.
[8]	顾韶竹, 应宇欣, 张华杰, 等. 一种面向多源传感器的飞行器类型识别综合仿真方法[J]. 系统仿真学报, 2024, 36(1): 149-159.
	Gu Shaozhu, Ying Yuxin, Zhang Huajie, et al. A Simulation Method Based on Multi-source Sensors for Aircraft Type Identification[J]. Journal of System Simulation, 2024, 36(1): 149-159.
[9]	王续乔, 来飞龙, 赵昌丽. 多节链式倾转旋翼飞行器重构控制与运动仿真[J]. 北京航空航天大学学报, 2024, 50(5): 1523-1531.
	Wang Xuqiao, Lai Feilong, Zhao Changli. Reconfiguration Control and Motion Simulation of Tilt-rotor Aircraft with Multilinks[J]. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50(5): 1523-1531.
[10]	马艳艳, 林强, 牛闯, 等. 基于嵌入式粒子群算法的目标航迹模拟方法[J]. 现代防御技术, 2024, 52(5): 51-60.
	Ma Yanyan, Lin Qiang, Niu Chuang, et al. Simulation Method of Target Track Based on Embedded Particle Swarm Optimization Algorithm[J]. Modern Defence Technology, 2024, 52(5): 51-60.
[11]	刘玄冰, 周绍磊, 肖支才, 等. 固定翼无人机航迹跟踪抗风性研究[J]. 现代防御技术, 2022, 50(1): 41-47.
	Liu Xuanbing, Zhou Shaolei, Xiao Zhicai, et al. Wind Resistance of Fixed-wing UAV Path Tracking[J]. Modern Defence Technology, 2022, 50(1): 41-47.
[12]	谭顺成, 陈中华, 于洪波. 分布式2D雷达网的航迹关联方法[J]. 现代防御技术, 2021, 49(4): 49-55, 63.
	Tan Shuncheng, Chen Zhonghua, Yu Hongbo. Track Association in Distributed 2D Radar Network[J]. Modern Defence Technology, 2021, 49(4): 49-55, 63.
[13]	沈一超, 倪世宏, 张鹏. 基于贝叶斯网络的飞行动作识别方法[J]. 计算机工程与应用, 2017, 53(24): 161-167, 218.
	Shen Yichao, Ni Shihong, Zhang Peng. Flight Action Recognition Method Based on Bayesian Network[J]. Computer Engineering and Applications, 2017, 53(24): 161-167, 218.
[14]	刘庆利, 李蕊, 乔晨昊. 基于改进支持向量回归的空战飞行动作识别[J]. 现代防御技术, 2024, 52(1): 49-56.
	Liu Qingli, Li Rui, Qiao Chenhao. Air Combat Flight Action Recognition Based on Improved Support Vector Regression[J]. Modern Defence Technology, 2024, 52(1): 49-56.
[15]	周超, 樊蓉, 张戈, 等. 基于多元时间序列融合的飞行动作识别方法[J]. 空军工程大学学报(自然科学版), 2017, 18(4): 34-39.
	Zhou Chao, Fan Rong, Zhang Ge, et al. A Flight Action Recognition Based on Multivariate Time Series Fusion[J]. Journal of Air Force Engineering University(Natural Science Edition), 2017, 18(4): 34-39.
[16]	Wei Zhenglei, Ding Dali, Zhou Huan, et al. A Flight Maneuver Recognition Method Based on Multi-strategy Affine Canonical Time Warping[J]. Applied Soft Computing, 2020, 95: 106527.
[17]	Tian Wei, Zhang Hong, Li Hui, et al. Flight Maneuver Intelligent Recognition Based on Deep Variational Autoencoder Network[J]. EURASIP Journal on Advances in Signal Processing, 2022, 2022(1): 21.
[18]	Lu Jing, Chai Hongjun, Jia Ruchun. A General Framework for Flight Maneuvers Automatic Recognition[J]. Mathematics, 2022, 10(7): 1196.
[19]	Bulbule Shamal, Soma Shridevi. Enhanced AlexNet for Detecting the Myocardial Infarction: An Efficient Approach[J/OL]. International Journal of Image and Graphics, 2024: 2650013. (2024-08-29) [2024-10-19]. .
[20]	Intan Nurma Yulita, Anton Satria Prabuwono, Ardiansyah Firman, et al. Pest Detection in Agricultural Farms Using SqueezeNet and Multi-layer Perceptron Model[J]. International Journal of Advanced Computer Science and Applications, 2024, 15(6): 802-808.
[21]	王兴隆, 许晏丰. 基于AM-LSTM的飞行区航空器滑行轨迹预测与冲突识别[J]. 中国安全科学学报, 2024, 34(1): 116-124.
	Wang Xinglong, Xu Yanfeng. Aircraft Taxiing Trajectory Prediction and Conflict Risk Identification in Airfield Area Based on AM-LSTM[J]. China Safety Science Journal, 2024, 34(1): 116-124.
[22]	钱来, 王伟. 一种基于C-GRU飞行轨迹预测方法[J]. 电子测量技术, 2022, 45(10): 87-92.
	Qian Lai, Wang Wei. A C-GRU Based Flight Trajectory Prediction Method[J]. Electronic Measurement Technology, 2022, 45(10): 87-92.

变量	初始化范围
经度/(°)	[-180, 180]
纬度/(°)	[-90, 90]
海拔/m	[300, 10 000]
速度/(m/s)	[200, 500]
轨迹形状	{直线，圆形，八字，跑道}
噪声强度	{低,中,高}

模型	模型类型	准确率/%	Macro-F1/%
AlexNet	图像模型	92.27	90.65
SqueezeNet	图像模型	87.26	83.23
GRU	序列模型	92.66	81.82
LSTM	序列模型	91.89	80.81
简单平均融合模型	混合模型	91.11	85.17
自适应权重融合模型	混合模型	87.64	83.37
多层感知机融合模型	混合模型	94.59	91.72

模型	轨迹形状真值
模型	形状	线形	圆形	八字	圆弧	跑道
多层感知机融合模型	线形	22	0	0	2	0
	圆形	0	96	4	0	2
	八字	0	0	72	0	0
	圆弧	0	1	1	13	4
	跑道	0	0	0	0	42