A Novel Hybrid Recurrent Wavelet Neural Network Control for a PMSM Drive Electric Scooter Using Rotor Flux Estimator

摘要

The electric scooter with nonlinear friction force of the transmission belt made the hybrid recurrent fuzzy neural network (HRFNN) control system with degenerated tracking responses. In order to overcome this problem, a novel hybrid recurrent wavelet neural network (NHRWNN) control system is proposed to control for a permanent magnet synchronous motor (PMSM) drive electric scooter. The NHRWNN control system consists of a supervisor control, a R WNN and a compensated control with adaptive law. Moreover, a NHR WNN control system using rotor flux estimator with sliding mode current observer is developed to reduce encoder interference and cost down. The on-line parameter training methodology of the RWNN can be derived using adaptation laws and the Lyapunov stability theorem. The RWNN has the on-line learning ability to respond to the system 's nonlinear and time-varying behaviors. To show the effectiveness of the proposed controller, comparative studies with HRFNN control system are demonstrated by experimental results.