The research of PMSM drive based on wavelet neural network space vector PWM

The basid principle of space vector pulse width modulation (SVPWM) is analyzed, and a algorithm of SVPWM based on wavelet neural network (WNN-SVPWM) is proposed. The comparative study between BP neural network space vector pulse width modulation (BP-SVPWM) and WNN-SVPWM is done. The simulation results show that the permanent magnet synchronous motor (PMSM) controlled by WNN-SVPWM has less total current harmonic distortion and pulsating torque than BP-SVPWM. The closed-loop PMSM control system controlled by WNN-SVPWM is researched, and the experimental results show that the voltage and current waves are perfect, and the motor works well.