Recognition of Radar Active Jamming Signal Based on Attention Mechanism

Aiming at the problem that radar active jamming signal cannot be recognized effectively in complex background, a recognition algorithm of radar active jamming signal based on attention mechanism is proposed. Firstly, the time-frequency map of the interference signal is input into the feature extraction network to obtain the depth feature. Then, the attention mechanism is introduced to locate the location of interference signal through RPN network to get the region of interest. Finally, the type of interference signal is identified for the region of interest. The simulation results show that the algorithm can locate, recognize and separate jamming signals in complex background. Compared with convolution neural network, the training sample is reduced by half, and the training efficiency is improved. At the same time, the overall recognition accuracy is improved by 10%, which can reach 95%.