Adaptive Iterative Learning Control for Tank Gun Servo Systems With Input Deadzone

In this paper, an adaptive iterative learning control scheme is proposed to solve the trajectory-tracking problem for tank gun servo systems with input deadzone and arbitrary initial states. A time-varying boundary layer is constructed to deal with the nonzero initial error during the iterative learning controller design. Neural network control and robust control are jointly used to compensate uncertainties and deadzone nonlinearity. The ideal weight of neural network and the upper bound of noncontinuous uncertainties are estimated by using difference learning method. As the iteration number increases, the filtering error can converge to the time-varying boundary layer. All signal are guaranteed to be bounded. A simulation example is presented to verify the effectiveness of the proposed scheme.