Waveform Recognition of UAV Swarm Communication in Multipath Channel

Abstract

The electromagnetic environment of UAV swarm communication is complex, and phenomena such as user interference, multipath fading and frequency shift occur. The performance of the waveform recognition algorithm under the traditional AWGN channel is greatly reduced in this scenario. To solve this problem, this paper proposes a waveform recognition algorithm for UAV swarm communication in multipath channel. Firstly, establish the multipath fading channel model of UAV swarm communication under Alpha pulse interference. Then, aiming at the problem of Alpha pulse interference among swarm users, extract the generalized cyclic mean and generalized cyclic spectrum features of the signal, and establish the waveform feature matrix of UAV swarm communication in multipath environment. Finally, the SAE deep neural network UAV swarm communication waveform recognition model is established. The simulation results show that the algorithm proposed in this paper has strong robustness in the complex environment of Alpha pulse interference, multipath fading and frequency shift, and realizes the recognition of six kinds of UAV swarm communication waveforms. At the same time, the recognition accuracy of more than 80% can be guaranteed when the signal-to-noise ratio is -10 dB.