Research on Radar Active Jamming Recognition Based on 2-D Time-Frequency Features

Electronic countermeasures are becoming increasingly fierce in modern warfare. The identification of jamming signals is an important means to improve the anti-jamming performance of radars. This paper proposes an algorithm based on the singular value distribution and instantaneous frequency two-dimensional characteristics of the radar active jamming signal in the time-frequency domain, and constructing a BP neural network to realize the jamming type identification. This paper first constructs six typical models of active jamming signal, and then sends the extracted two-dimensional parameters composed of singular value distribution (SVD) and instantaneous frequency (IF) to the BP neural network for training and recognition. The simulation results show that the algorithm has high and stable recognition results for all six typical jamming signals in a low jamming-to-noise ratio and small sample environment.