Abstract:The individual identification technology of radar emitter is to determine the identity attribute of the carrier by extracting the subtle features of the radar, and the basis of the individual identification of radar emitter signals is to correctly sort the multi-channel aliasing received signals in a complex electromagnetic environment. In order to solve the problem that the traditional signal sorting based on interpulse parameters is easy to cause incorrect pulse classification, this paper proposes a clustering algorithm based on interpulse parameters combined with intra-pulse bispectral features, which firstly constructs a feature matrix of bispectral waveform entropy composed of signal carrier frequency, pulse width and pulse enclosure integral, and then uses the improved adaptive DBSCAN clustering algorithm to cluster the feature matrix. The simulation results show that the proposed algorithm is verified by real data collection, and the classification accuracy is about 90%, which can meet the needs of subsequent individual identification.