The purpose of this paper is to investigate and implement a novel approach to learning control for permanent magnet synchronous motor (PMSM) drive system using a hybrid recurrent fuzzy neural network (HRFNN) control. First, the field-oriented mechanism is applied to formulate the dynamic equation of the PMSM servo drive. Then, a HRFNN speed control system that combined supervisor control, RFNN and compensated control is developed to control PMSM drive system. Finally, the effectiveness of the proposed control scheme is verified by the experimental results.