Robust adaptive neural network control for switched reluctance motor drives. (2nd January 2018)

• Record Type: Journal Article
• Authors: Li, Cunhe; Wang, Guofeng; Li, Yan; Xu, Aide
• Is Part Of: Automatika. Volume 59:Number 1(2018)
• Page Start: 24
• Page End: 34
• Publication Date: 2018-01-02
• Subjects: Switched reluctance motor -- speed control -- adaptive neural network control -- parameter variations -- external load disturbances; Automatic control -- Periodicals; 629.805
• DOI: 10.1080/00051144.2018.1486797
• Languages: English
• ISSNs: 0005-1144

Abstract

ABSTRACT: This article presents a robust adaptive neural network controller for switched reluctance motor (SRM) speed control with both parameter variations and external load disturbances. The radial basis function neural network with the technology of minimal learning parameters is employed to approximate an ideal control law which includes the parameter variations and external disturbances. Furthermore, a proportional control term is introduced to improve the transient performance and chattering phenomena of the SRM drive system. The asymptotic stability of the proposed controller is guaranteed through rigorous Lyapunov analysis. A main advantage of the proposed control scheme is that it contains only one adaptive parameter that needs to be updated on-line. This advantage result in a much simpler adaptive control algorithm, which is convenient to implement in switched reluctance drives. Finally, the simulations and experiments are carried out to demonstrate the effectiveness of the proposed control scheme.