In modern times, radar detection faces the additively compounded jamming signals emitted by multiple jammers. Due to the unknown number, type, and parameters of individual jamming signals, previous jamming recognition algorithms cannot identify all compound cases. During network model training, it becomes necessary to predefine the type of compound jamming signals, and it also limits the number of labels for samples, from which only specific compound cases can be recognized. In this article, a recognition strategy named “Separation + Recovery + Recognition” is proposed to identify all the jamming cases of additively compounded jamming effectively. First, the number of signal sources of the received signals from multiple channels is analyzed. Next, the separated single jamming signal is obtained by source separation method from the received additively compounded signals. And then the radar signal recovery network is used to compensate and recover signals that are incompletely separated due to the time-frequency overlap. Finally, the separated and recovered single jamming signals are put into the designed convolutional neural network model for recognition. The simulation results show that the proposed algorithm demonstrates superior performances in recognition and generalization. When the jamming-to-noise ratio is −10 dB, the recognition accuracy of the compound case of five jamming signals can still reach 90% plus.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Radar Compound Jamming Recognition Method Based on Blind Source Separation


    Beteiligte:
    Zhou, Hongping (Autor:in) / Wang, Lei (Autor:in) / Guo, Zhongyi (Autor:in)


    Erscheinungsdatum :

    01.12.2024


    Format / Umfang :

    1825463 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Recognition of Radar Compound Jamming Based on Convolutional Neural Network

    Zhou, Hongping / Wang, Lei / Guo, Zhongyi | IEEE | 2023



    ADS-B degarbling and jamming mitigation by the use of Blind Source Separation

    Leonardi, Mauro / Giuseppe Piracci, Emilio | IEEE | 2018


    Shift-frequency jamming suppression technique based on polarized channel expanding and blind source separation union

    Li, Xin / Wang, Chunyang / Fu, Xiaolong et al. | British Library Online Contents | 2017


    Radar Compound Jamming Cognition Based on a Deep Object Detection Network

    Zhang, Jiaxiang / Liang, Zhennan / Zhou, Chao et al. | IEEE | 2023