Online speed control of permanent-magnet synchronous motor using self-constructing recurrent fuzzy neural network

In this paper, a self-constructing recurrent fuzzy neural network (SCRFNN) method is proposed to control the speed of a permanent-magnet synchronous motor to track periodic reference trajectories. The proposed SCRFNN combines the merits of self-constructing fuzzy neural network (SCFNN) and the recurrent neural network (RNN). The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient-decent method. In addition, the Mahalanobis distance (M-distance) formula is employed that the neural network has the ability of identification of the neurons will be generated or not. Finally, the simulated results show that the control effort is robust.