Neural network control schemes for PM spherical stepper motor drive

Abstract

This paper presents three control schemes for PM spherical stepper motor drive. In the neural network PD control scheme, the neural network is used to train the control parameters online. Based on the non-linear system dynamic model under continuous trajectory tracking mode, the robust neural network control scheme is presented to eliminate uncertainties to improve the trajectory tracking robust stability and overcome the undesired influence of the uncertainties. The adaptive fault accommodation neural network control scheme assures the convergence of the estimate errors of the neural network and the fault-monitoring system in the presence of system uncertainties. Simulations of the proposed control scheme on the spherical stepper motor system demonstrate the effectiveness on satisfactory tracking performance.