Frequency agility radar time-frequency domain joint interference method based on fuzzy reinforcement learning

The invention discloses a frequency agility radar time-frequency domain joint interference method based on fuzzy reinforcement learning, and the method comprises the steps: building a target echo model and an interference signal model according to a radar signal processing flow, taking a jammer as a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LI SHILONG, LIAO MAOSEN, GAN LINCHUAN, CUI GUOLONG, XIONG KUI, KONG LINGJIANG, YANG XIAOBO, YU XIANXIANG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a frequency agility radar time-frequency domain joint interference method based on fuzzy reinforcement learning, and the method comprises the steps: building a target echo model and an interference signal model according to a radar signal processing flow, taking a jammer as an intelligent agent, modeling a jammer time-frequency domain joint interference process as a generalized Markov decision process, and carrying out the time-frequency domain joint interference process; a state value function is obtained, a proposed time domain fuzzy Q learning algorithm and a frequency domain Q learning algorithm are used for joint solving, and finally the interference time and carrier frequency selection strategy of the jammer is obtained. According to the method, an interference process is modeled as a generalized Markov decision process, selection of an interference machine carrier frequency in a frequency domain is regarded as an action, radar carrier frequency is regarded as a state, selection