Analysis of motion interference characteristics of underwater vehicles salvo based on the RBF Neural Network

Abstract

Compared with the launch process of a single underwater vehicle, the salvo of multiple vehicles is more complex and needs to be more deeply studied. When the first vehicle is launched, it will disturb the flow field and affect the attitudes and trajectories of the subsequent vehicles. If the impact range is not clearly defined, the launch safety will be threatened. In this paper, we outline the underwater salvo process of two vehicles. A RBF (radial basis function) neural network model is established, which is driven by data generated through numerical simulation. The model is applied to predict the interference variation law of motion characteristic variables that the first vehicle to the second under different launch conditions. The results show that the RBF neural network model can predict the interference of the motion characteristic variables that the first vehicle to the second vehicle in the process of salvo, which is more effective and accurate than the numerical simulation and experimental methods. In addition, the results reveal the influence of the first vehicle on the deflection angle and displacement of the second vehicle under different launch parameters, in which the launch time interval is the most sensitive factor affecting the motion characteristics of the vehicle.