Electromagnetic signal identification method based on two-layer cascade convolutional neural network

The invention discloses an electromagnetic signal identification method based on a two-layer cascade convolutional neural network, and the method comprises the steps: carrying out the preprocessing of an unknown electromagnetic signal, and obtaining six modulation features and seven time-frequency features of the electromagnetic signal; taking the six modulation features as input of a first layer of cascaded convolutional neural network, wherein the first layer of cascaded convolutional neural network outputs a modulation mode of an electromagnetic signal; and taking the acquired seven time-frequency characteristics and the electromagnetic signal modulation mode output by the first layer of cascaded convolutional neural network as the input of a second layer of cascaded convolutional neural network, wherein the second layer of cascaded convolutional neural network outputs the signal type of the electromagnetic signal. According to the method, the two-layer cascade convolutional neural network is constructed a