Radar signal intra-pulse modulation identification method based on FSST2 and convolutional neural network

The invention relates to a radar signal intra-pulse modulation recognition method based on FSST2 and a convolutional neural network, and belongs to the field of radar signal processing. Graying and bilinear size transformation preprocessing are performed on the time-frequency images of seven radar intra-pulse modulation signals generated based on FSST2, so that the obtained time-frequency images are better in noise immunity and higher in time-frequency aggregation degree. Furthermore, deep convolution and point-by-point convolution are combined to construct a CNN network structure which is high in convergence speed and higher in recognition rate, and training and testing are carried out. A simulation experiment verifies the effectiveness of the method, and compared with a method adopting other time-frequency graphs and other neural network structures, the method provided by the invention has a higher classification recognition rate on seven kinds of radar intra-pulse modulation signals in a low signal-to-nois