Novel adaptive modified recurrent Legendre neural network control for a PMSM servo-driven electric scooter with V-belt continuously variable transmission system dynamics. (November 2015)

• Record Type: Journal Article
• Authors: Lin, Chih-Hong
• Is Part Of: Transactions of the Institute of Measurement and Control. Volume 37:Number 10(2015)
• Page Start: 1181
• Page End: 1196
• Publication Date: 2015-11
• Subjects: Permanent magnet synchronous motor -- modified recurrent Legendre neural network -- Lyapunov stability theorem; Automatic control -- Periodicals; Measuring instruments -- Periodicals; Commande automatique -- Périodiques; Mesure -- Instruments -- Périodiques; 681.2
• DOI: 10.1177/0142331214558105
• Languages: English
• ISSNs: 0142-3312

Abstract

Because of the unknown nonlinearity and time-varying characteristics of a V-belt continuously variable transmission (CVT) driven electric scooter system using a permanent magnet synchronous motor (PMSM) servo drive, its accurate dynamic model is difficult to establish for the design of the linear controller in the whole system. In order to conquer this difficulty and increase robustness, a novel adaptive modified recurrent Legendre neural network (NN) control system is proposed for controlling a PMSM servo-driven electric scooter with a V-belt CVT system. The novel adaptive modified recurrent Legendre NN control system consists of a modified recurrent Legendre NN control with adaptation law and a compensated control with estimation law. Additionally, the online parameter tuning methodology of the modified recurrent Legendre NN control and the estimation law of the compensated control can be derived by using the Lyapunov stability theorem. Furthermore, two optimal learning rates of the modified recurrent Legendre NN are proposed according to a discrete-type Lyapunov function in order to raise the speed of convergence. Finally, comparative studies are provided by experimental results in order to show the effectiveness of the proposed control scheme.