Neural sliding mode control for tracking of axis of firepower of unmanned turret

Referring to the problems of system parameter perturbation caused by fire aiming mechanism existed in tracking system of axis of firepower of unmanned turret and external disturbances existed in system input while gun is firing, a neural sliding mode control strategy is given. This approach uses a nonsingular terminal sliding mode manifold to guarantee that the controlled system can reach the sliding mode manifold and equilibrium point in finite time from any initial state. A Radial Basis Function (RBF) neural network is applied to compensate adaptively the upper bound of uncertainty, and to ensure the sliding mode motion. The stability of the controller and the convergence of the tracking error of axis of firepower are proven by Lyapunov criterion. The simulation results show that the accuracy and robustness of tracking control of the axis of firepower are guaranteed, and chattering of the sliding mode control is reduced by the RBF neural network's learning without sacrificing its robustness. The control scheme is valid.