Low-Complexity Neural Back-Stepping Control with Improved Prescribed Performance for Waverider Vehicles

It is well known that waverider vehicles have several potential uses in the aerospace industry. In this study, a low-complexity neural back-stepping control approach for waverider vehicles that is susceptible to input saturations is described. To begin with, a reliable back-stepping controller with a simple radial basis neural network is created for the usual waverider vehicle model. Then, a better prescribed performance control strategy for waverider vehicles is used to deal with the fragile problem of prescribed performance control (PPC) methods due to actuator saturations, which can ensure tracking errors satisfy the anticipated transient performance with input saturations. Finally, MATLAB simulations with perturbed aerodynamic parameters are used to demonstrate the efficiency of the suggested control schemes.