Radar signal working mode identification method and system based on deep learning network

The invention belongs to the technical field of radar signal working mode recognition in electronic countermeasure, and discloses a radar signal working mode recognition method and system based on a deep learning network, and the method comprises the steps: enabling a receiver to receive a radar pulse signal, gathering pulses in the same coherent pulse group, and building a pulse group; fitting amplitude of pulses in the same pulse group, carrying out FFT transformation on the pulses, wherein pulse description words and frequency spectrum amplitudes serve as primary features; performing feature fusion on the primary features by using local preserving canonical correlation analysis; and inputting the obtained feature vector into a sparse deep belief network based on a smooth L0 norm, and finally performing classification identification through softmax. The sparse penalty term is added on the basis of the deep belief network, and the sparse deep neural network is established, so that theoperation efficiency is