Recurrent wavelet neural network control of a PMSG system based on a PMSM wind turbine emulator

Abstract

A recurrent wavelet neural network (NN)-controlled 3-phase permanent magnet synchronous generator system (PMSG), which is direct-driven by a permanent magnet synchronous motor (PMSM) based on a wind turbine emulator, is proposed to control the output values of a rectifier (or AC to DC power converter) and inverter (or DC to AC power converter) in this study. First, a closed-loop PMSM drive control based on a wind turbine emulator is designed to generate the maximum power for the PM synchronous generator (PMSG) system according to different wind speeds. Next, the rotor speed of the PMSG, the DC bus voltage, and the current of the power converter are detected simultaneously to yield a better power output of the converter through DC bus power control. Because the PMSG system is a nonlinear and time-varying dynamic system, one online-trained recurrent wavelet NN controller is developed for the tracking controller of the DC bus power to improve the control performance in the output end of the rectifier. Additionally, another online-trained recurrent wavelet NN controller is also developed for tracking the controller of the AC power to improve the control performance in the output end of the inverter. Finally, some experimental results are verified to show the effectiveness of the proposed recurrent wavelet NN-controlled PMSG system direct-driven by a PMSM based on a wind turbine emulator.