Prediction on EMS of UAV's Data Link Based on SSA-Optimized Dual-Channel CNN

Abstract

In this article, a novel method is presented for electromagnetic interference (EMI) perception and electromagnetic susceptibility (EMS) assessment of an unmanned aerial vehicle (UAV) against interference. A large number of in-phase and quadrature data of the UAV's data link and their corresponding critical EMI signal were collected by the equivalent injection test method. After visualization and preprocessing of the in-phase and quadrature data, the obtained time–frequency spectrum and the data-link state parameter histogram were joined to further preprocess as the input of the model. A dual-channel convolutional neural network optimized by a sparrow search algorithm (SSA-DCNN) was proposed to predict the EMS of the data link of the UAV. The proposed method can not only avoid manual extraction of data features but also improve the intelligence level of EMI perception and safety evaluation on UAVs. The performance of the dual-channel convolutional neural network is compared with that of the SSA-DCNN method under different optimization algorithms. The results show that the SSA-DCNN model can significantly enhance the convergence speed and prediction accuracy of the training process compared with the dual-channel convolutional neural network. Besides, among the optimization algorithms, the stochastic gradient descent with momentum applied to the SSA-DCNN model shows a better performance.