Dense False Target Jamming Recognition Based on Fast-Slow Time Domain Joint Frequency Response Features

Dense false target jamming (DFTJ) is one of the most common and threatening jamming modes, seriously affecting a radar from detecting a target. This article counters DFTJ by proposing a fast-slow time domain joint frequency response feature-based jamming recognition method that utilizes the differences in the frequency response characteristics of the radar and digital radio frequency memory (DRFM) jammer. The core idea of this method is to model the influence of the radar's and DRFM jammer's frequency response characteristics on the frequency response features of the target echo and jamming signal. In addition, the developed strategy extends the influence from the fast-time domain to the fast-slow time domain through pulse compression and coherent accumulation processing. Then, the fast-slow time domain joint amplitude-frequency response features of both signals are combined to construct a training dataset. Finally, a dual-channel feature fusion network (1DCNN-LSTM) comprising a 1-D convolutional neural network (1DCNN) and a long short-term memory network (LSTM) is constructed for jamming recognition. The effectiveness of the proposed method is proven through simulated and measured experiments. The results show that the proposed method can achieve a recognition accuracy of 98.9% and 96% on the two measured data experiments, respectively.