Adaptive neural control of Supercavitated vehicles base on LMI

Abstract

supercavitation technology is effective in reducing the resistance of the navigating body to the flow of seawater, thereby increasing the speed of movement. However, when the navigating body is encapsulated by the hollow bubble, it reduces most of the buoyancy force it is subjected to and the planning force generated when the wake collides with the hollow bubble wall, making it difficult to stabilise the supercavitated vehicles during its movement. In this paper, a neural network adaptive control method based on linear matrix inequalities (LMI) is designed to address this problem. The neural network adaptive control law is derived using the linear matrix inequality, the output of the neural network is approximated to the uncertainty value in the model, and then the controller is derived. The simulation results show that the designed controller has good stability and the ability to track step signals.