Hybrid recurrent wavelet neural network control of PMSM servo-drive system for electric scooter

Due to nonlinear uncertainties of the electric scooter such as nonlinear friction force of the transmission belt and clutch, these will lead to degenerate tracking responses in command current and speed of the permanent magnet synchronous motor (PMSM) servo-driven electric scooter. In this study a novel hybrid recurrent wavelet neural network (HRWNN) control system is proposed to raise robustness of the PMSM servo-driven electric scooter under the occurrence of the variation of rotor inertia and load torque disturbance. First, the field-oriented mechanism is applied to formulate the dynamic equation of the PMSM servo drive. Then, a novel HRWNN control system is proposed to control motion for a PMSM servo-driven electric scooter. The HRWNN control system composed of a supervisor control, a RWNN and a compensated control with adaptive law. The online parameter training methodology with adaptive law in the RWNN is derived based on the Lyapunov stability theorem. Then adaptive law of the parameter in the RWNN can be updated by using the gradient descent method and the backpropagation algorithm. Finally, the effectiveness of the proposed control scheme is verified by experimental results.