摘要
针对传统航迹相似性研究中,聚类算法在高维度数据,特别是复杂航迹条件下航迹识别结果模糊,聚类效果不精确,时间成本开销较大的问题,提出一种基于改进随机深度网络的航迹分类与异常检测模型。首先,在残差网络模型的基础上,优化设计了注意力机制(SE)模块和全局平均池化(GAP)模块,并构建了航迹分类网络模型。其次,在数据处理阶段利用连续时空航迹模型,将离散的航迹数据转换为连续的特征图数据,以便于图神经网络处理。然后,在航迹分类训练集中引入标称航迹,实现以标称航迹作为参照进行航迹分类。最后,在航迹分类结果的基础上,设计了改进的孪生神经网络进行异常航迹检测。综合实验表明,相较于聚类算法,本文算法能够高效完成按照标称航迹进行航迹分类的任务,并能精确检测异常航迹。
In traditional trajectory similarity research,clustering algorithms have the problems of indistinct trajectory identification results,imprecise clustering,and larger time cost under the condition of high-dimensional data,espe⁃cially under the condition of complex trajectory.To address these issues,we present a trajectory classification and anomaly detection model based on the improved stochastic depth network.Firstly,we optimize the attention mecha⁃nism Squeezed-and-Excitation(SE)module and Global Average Pool(GAP)module based on the ResNet model,and construct a trajectory classification network model.Secondly,in the data processing stage,the continuous spatio⁃temporal trajectory model is used to convert the discrete trajectory data into continuous data of the trajectory function of time for graph neural network processing.Then,nominal trajectory data is introduced into the training set to realize tra⁃jectory classification,with nominal trajectories as the reference.Finally,an improved twin neural network is developed based on the trajectory classification results,and is utilized for abnormal trajectory detection.Comprehensive experi⁃ments show that the proposed algorithm can efficiently complete the task of track classification according to nominal trajectories and detect abnormal trajectories accurately,compared with traditional track clustering algorithms.
作者
宋歌
韩鹏飞
罗钰翔
潘卫军
SONG Ge;HAN Pengfei;LUO Yuxiang;PAN Weijun(College of Air Traffic Management,Civil Aviation Flight University of China,Guanghan 210016,China)
出处
《航空学报》
北大核心
2025年第4期242-260,共19页
Acta Aeronautica et Astronautica Sinica
基金
国家自然科学基金(U2333209)
民航局安全能力建设基金(MHAQ2022008)。
关键词
航迹相似性
航迹分类
随机深度网络
异常检测
民用航空
trajectory similarity
trajectory classification
stochastic depth ResNet
anomaly detection
civil aviation
