This article analyzes the operational characteristics of two deep learning algorithms, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), and proposes a radar radiation source recognition method based on Coupled Recurrent Network (CRN). Its feasibility is verified through simulation experiments. When the signal-to-noise ratio of the test set signal is 3dB, the algorithm still has a recognition rate of 82.73% for the signal, while when the signal-to-noise ratio of the test set signal is greater than or equal to 5dB, the recognition rate of the algorithm for signals exceeds 94.70%.