Dynamic main lobe interference resisting method based on DQN

The invention discloses a DQN-based dynamic main lobe interference resisting method, and relates to the technical field of radar signal processing, and the method comprises the steps: obtaining an echo signal, carrying out the sampling processing of the echo signal, and obtaining echo signal data; obtaining a module value of the echo signal data to obtain a module value vector of the echo signal; processing the module value vector of the echo signal by using a trained main lobe interference resisting strategy selection model to obtain a coding vector; according to the coding vector, determining a selection action corresponding to the trained main lobe interference resisting strategy selection model; according to the selection action, determining a corresponding main lobe interference resisting strategy; wherein each selection action corresponds to one main lobe interference resisting strategy. Based on the DQN framework, dynamic strategy selection can be carried out on multiple main lobe interference resistin