The Hypersonic Glide Vehicle (HGV) has become a focal point in military competitions among nations. Predicting the real-time trajectory of an HGV is of significant importance for aerospace defense interception and assessing enemy combat intentions. Existing prediction methods are limited by the need for large data samples and poor general applicability. To address these challenges, this paper presents a novel trajectory forecasting approach based on the Sparse Association Structure Model (SASM). The SASM can uncover the relationship among known data, transfer associative relationships to unknown data, and improve the generalization of the model. Firstly, a trajectory database is established for different maneuvering modes based on the six-degree-of-freedom motion equations and models of attack and bank angles of the HGV. Subsequently, three trajectory parameters are selected as prediction variables according to the maneuvering characteristics of the HGV. A parameters prediction model based on the SASM is then constructed to predict trajectory parameters. The SASM model demonstrates high accuracy and generalization in forecasting the trajectories of three different HGV types. Experimental results show a 50.35% reduction in prediction error and a 48.7% decrease in average processing time compared to the LSTM model, highlighting the effectiveness of the proposed method for real-time trajectory forecasting.


    Access

    Download


    Export, share and cite



    Title :

    Intelligent Trajectory Prediction Algorithm for Hypersonic Vehicle Based on Sparse Associative Structure Model


    Contributors:
    Furong Liu (author) / Lina Lu (author) / Zhiheng Zhang (author) / Yu Xie (author) / Jing Chen (author)


    Publication date :

    2024




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Transfer Learning for Hypersonic Vehicle Trajectory Prediction

    Bartusiak, Emily R. / Jacobs, Michael A. / Spells, Corbin F. et al. | IEEE | 2023


    Intelligent Trajectory Predicting of Hypersonic Vehicle Using LSTM

    Yuanjie, Meng / Chunqiao, Dan / Jin, Zhang et al. | Springer Verlag | 2023




    Hypersonic Vehicle Reentry Trajectory Optimization Based on Particle Swarm Algorithm

    Haiqing, Wang / Junfeng, Jiang / Xinlu, Guo et al. | Springer Verlag | 2025