The invention discloses an aircraft trajectory prediction method based on an LSTM-DNN hybrid neural network, and relates to the field of civil aircraft trajectory prediction, and the method comprises the following steps: S1, screening aircraft trajectory prediction model input, collecting ADS-B data, and processing missing data through a data fitting method; s2, predicting a future flight trajectory by using an LSTM long and short term prediction model; s3, adopting a DNN deep feedforward neural network model to predict the flight path deviation of the next time point; s4, using the prediction result of the high-precision model to correct the prediction result of the low-precision model; and S5, according to a trajectory prediction result, adopting a separation distance to indicate the flight safety of the two flights at the future moment. By adopting the above steps, two neural network models are constructed, the deviation between the actual flight path and the target flight path and the long-term prediction of the future flight path are respectively predicted, the prediction results of the two models are fitted together through the error term, and the long-term high-precision prediction of the flight path is realized.

    本发明公开了一种基于LSTM‑DNN混合神经网络的航空器轨迹预测方法,涉及民用航空器航迹预测领域,包括以下步骤:S1:筛选航空器轨迹预测模型输入,收集ADS‑B数据,采用数据拟合的方法处理缺失数据;S2:采用LSTM长短期预测模型预测未来飞行轨迹;S3:采用DNN深度前馈神经网络模型预测下一时间点的飞行轨迹偏差;S4:用高精度模型的预测结果去修正较低精度模型的预测结果;S5:根据轨迹预测结果采用分离距离表明两个航班在未来时刻的飞行安全性。本发明采用上述步骤,构建了两种神经网络模型,分别预测实际飞行轨迹和目标飞行轨迹之间的偏差以及对未来飞行轨迹的长期预测,通过误差项将两个模型预测结果拟合到一起,实现了对飞行轨迹的长期高精准预测。


    Access

    Download


    Export, share and cite



    Title :

    Aircraft trajectory prediction method based on LSTM-DNN hybrid neural network


    Additional title:

    一种基于LSTM-DNN混合神经网络的航空器轨迹预测方法


    Contributors:
    WANG ZHONGYE (author) / ZHANG SHIJIA (author) / ZHANG HONGHAI (author) / OUYANG YUXIANG (author) / LIU HAO (author) / ZHONG GANG (author)

    Publication date :

    2023-09-29


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Aircraft Trajectory Prediction Using Social LSTM Neural Network

    Xu, Zhengfeng / Zeng, Weili / Chen, Lijing et al. | TIBKAT | 2021


    Vehicle trajectory prediction based on LSTM network

    Yang, Zhifang / Liu, Dun / Ma, Li | IEEE | 2022


    Vehicle Trajectory Prediction based on LSTM Recurrent Neural Networks

    Ip, Andre / Irio, Luis / Oliveira, Rodolfo | IEEE | 2021


    An LSTM network for highway trajectory prediction

    Altche, Florent / de La Fortelle, Arnaud | IEEE | 2017


    Flight Trajectory Prediction of General Aviation Aircraft Based on LSTM Model

    Wang, Biao / Zhai, Zhengang / Xiong, Renhao et al. | IEEE | 2021