Wireless communication modulation mode identification method based on space-time diagram convolutional neural network

The invention discloses a wireless communication modulation mode identification method based on a space-time diagram convolutional neural network, and the method comprises the following steps: A, carrying out the time domain and frequency domain two-dimensional normalization processing of signal data of multiple modulation modes, and obtaining a radio frequency signal data set G containing time domain features and frequency domain features; b, performing extraction operation on the features of the radio frequency signal by using a convolutional neural network of a double-flow space-time diagram, and then performing aggregation operation to obtain a space-time feature sequence of deep fusion of global features and local features of the radio frequency signal; and C, identifying a wireless signal modulation mode by using an attention-based coding-decoding deep neural network model. According to the invention, the modulation mode of the radio frequency signal can be adaptively identified and classified. 本发明公开了一种