Radar signal sorting method based on point cloud segmentation network

The invention discloses a radar signal sorting method based on a point cloud segmentation network, and belongs to the field of electronic reconnaissance of information and communication engineering. The problems that parameter setting needs to depend on artificial experience, the sorting process is complex, the unknown signal sorting capacity is poor, and the radar signal sorting requirement in the current complex electromagnetic environment is difficult to meet in a traditional radar signal sorting method are solved. According to the method, a deep learning model is combined with radar signal sorting, an end-to-end sorting scheme without manual intervention from original PDW to EDW is directly realized, and the sorting implementation process is simplified. Moreover, the neural network can deeply mine the feature correlation between PDWs of different types of radars, so that the method still has a good sorting capability for unknown radar signals in a non-cooperative scene. The method can be applied to radar