Modulation identification method, device and equipment based on time-frequency graph and deep learning

• Main Authors: LIU WEI, HUANG YING, DENG ZHE, LEI JING, LIU PENGTAO
• Format: Patent
• Language: Chinese; English
• Published: 29.07.2022
• Subjects: ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to a modulation identification method and device based on a time-frequency graph and deep learning, computer equipment and a storage medium. The method comprises the following steps: carrying out wavelet transformation on a phase modulation signal to obtain a transformation result, converting a modulus value of the transformation result into a color map, and reconstructing the color map to obtain a wavelet transformation time-frequency map of the PSK type modulation signal; constructing a deep neural network according to the size of the wavelet transform time-frequency graph, the type of the PSK type modulation mode and the residual network; the deep neural network comprises a residual connection network and a random channel network; inputting the wavelet transform time-frequency graph into a residual connection network and a random channel network to obtain a plurality of recall rates of a PSK-type modulation mode; and performing fusion processing on the plurality of recall rates to obt