Simulation of UAV Interception and Countermeasure Based on Convolutional Neural Network

The simulation computer is the main body of the system, and the hardware and software of the system are designed on the basis of considering the two functional requirements of integrated UAV interception and counter-simulation. Firstly, the voices of unmanned aerial vehicles, birds and people within 100 m are collected, preprocessed and extracted with MFCC+GFCC eigenvalues, and their eigenvalues are used as data sets for learning and recognition by convolutional neural networks. Then, the interception model of UAV route planning based on convolutional neural network algorithm and the corresponding deception jamming counter-measure model are expounded. The model effect is simulated and evaluated by computer, and the convergence speed of the algorithm is discussed. The power and optimal deployment position and number of jammers are simulated under the condition that no base station is intercepted in 50 interception routes, thus proving the availability and accuracy of the jammer position planning model.