Fuzzy neural network design with switching strategy for permanent-magnet synchronous motor speed controller

In this paper, a self-constructing fuzzy neural network controller (SCFNNC) design with switching strategy for permanent-magnet synchronous motor is proposed to track periodic reference input command. The SCFNNC system is a straightforward implementation of fuzzy inference system with five layered neural network structure. This system combines the advantages of the neural networks and fuzzy logic theorem. To increase the on-line learning rate, the switching strategy is proposed to choice a suitable parameter of error term. First, the switching condition is defined by speed error. Next, we will judge whether the switching condition is satisfied through proposed switching regulator. Finally, the switching regulator is back-propagated to the SCFNNC and adjusted the link weights and other parameter. The simulation results for periodic reference trajectories show that the dynamic behavior of the proposed control system is robust with regard to plant parameter variations and external load disturbance.