Accurately predicting or calculating the missile’s flight path is one of the key challenges in applying the missile model to various related simulations. The traditional method used for this task is to use models and numerical integration, which requires a lot of computing resources. In this paper, a deep neural network with two hidden layers is established to predict the missile’s flight trajectory, the data generated by the traditional model is used to train and test the network, and the error of the network prediction result is analyzed. Using the trained DNN to predict the missile’s flight path is about four times faster than the traditional model, and the prediction error is small.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning Based Missile Trajectory Prediction


    Beteiligte:
    Wang, Zijian (Autor:in) / Zhang, Jinze (Autor:in) / Wei, Wei (Autor:in)


    Erscheinungsdatum :

    27.11.2020


    Format / Umfang :

    273037 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Trajectory Prediction of Vehicles Based on Deep Learning

    Jiang, Huatao / Chang, Lin / Li, Qing et al. | IEEE | 2019



    Trajectory Modeling and Simulation of Anti-missile Interception of Warship Based Missile

    Gao, Yunbo / Han, Liang / Wang, Jiangyun | British Library Conference Proceedings | 2016


    Trajectory Modeling and Simulation of Anti-missile Interception of Warship Based Missile

    Gao, Yunbo / Han, Liang / Wang, Jiangyun | Springer Verlag | 2016


    Phased Flight Trajectory Prediction with Deep Learning

    Zhang, Kai / Chen, Bowen | ArXiv | 2022

    Freier Zugriff