The invention particularly relates to an airspace operation complexity evaluation method based on a deep convolutional neural network. The airspace operation complexity evaluation method comprises thesteps of extracting sector dynamic traffic data of a target airspace sector, and performing airspace operation complexity grade marking; defining an external rectangle of the target airspace sector,and performing gridding processing; constructing a multi-channel air traffic situation image, and constructing an air traffic situation image library according to airspace operation complexity level marks; constructing an airspace operation complexity hierarchical network model according to the multi-channel air traffic situation image; training the airspace operation complexity hierarchical network model; and performing airspace operation complexity evaluation according to the trained airspace operation complexity hierarchical network model. Therefore, automatic learning of the most relevantcharacteristics from original data in an end-to-end manner is realized on the premise of not depending on complexity relevant characteristics, and the establishment of the airspace operation complexity hierarchical network model can be assisted, and the workload and the use threshold of airspace complexity assessment are greatly reduced.

    本发明具体涉及一种基于深度卷积神经网络的空域运行复杂度评估方法其包括:抽取目标空域扇区的扇区动态交通数据,并进行空域运行复杂性等级标注;划定目标空域扇区的外接矩形,并进行网格化处理;构造多通道空中交通态势图像,并根据空域运行复杂性等级标注构建空中交通态势图像库;根据多通道空中交通态势图像构建空域运行复杂性分级网络模型;对空域运行复杂性分级网络模型进行训练;以及根据训练后的空域运行复杂性分级网络模型进行空域运行复杂性评估,实现了在不依赖复杂度相关特征的前提下以“端到端”的方式自动从原始数据中进行学习最相关的特征,从而辅助空域运行复杂性分级网络模型的建立,大大降低了空域复杂度评估的工作量和使用门槛。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Airspace operation complexity evaluation method based on deep convolutional neural network


    Weitere Titelangaben:

    基于深度卷积神经网络的空域运行复杂度评估方法


    Beteiligte:
    XIE HUA (Autor:in) / ZHANG MINGHUA (Autor:in) / CHEN HAIYAN (Autor:in) / ZHU YONGWEN (Autor:in) / MAO JIZHI (Autor:in) / GE JIAMING (Autor:in) / TANG ZHILI (Autor:in) / WANG CHANGCHUN (Autor:in) / PU FAN (Autor:in) / YUAN LIGANG (Autor:in)

    Erscheinungsdatum :

    2021-03-12


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    An Airspace Complexity Evaluation System Based on Deep Learning

    SUN BO / WEI MING / TAN YINGJIA | Europäisches Patentamt | 2021

    Freier Zugriff

    A Deep Unsupervised Learning Approach for Airspace Complexity Evaluation

    Li, Biyue / Du, Wenbo / Zhang, Yu et al. | IEEE | 2022


    Defining Airspace Complexity

    Daniel Weckler / Bryan Matthews / Nikunj Oza et al. | NTRS



    Airspace complexity rasterizing evaluation method based on aircraft interaction relationship

    WANG HONGYONG / GUO YUPENG / NIE WENBINRUI et al. | Europäisches Patentamt | 2023

    Freier Zugriff