Direct adaptive neural network control for switched reluctance motors with input saturation. Issue 12 (22nd June 2018)

• Record Type: Journal Article
• Authors: Li, Cunhe; Wang, Guofeng; Li, Yan; Xu, Aide
• Is Part Of: IEEJ transactions on electrical and electronic engineering. Volume 13:Issue 12(2018)
• Page Start: 1804
• Page End: 1814
• Publication Date: 2018-06-22
• Subjects: switched reluctance motor -- speed control -- direct adaptive neural network -- parameter variations -- external load disturbances -- input saturation; Electrical engineering -- Periodicals; Electronics -- Periodicals; 621.3
• DOI: 10.1002/tee.22743
• Languages: English
• ISSNs: 1931-4973

Abstract

Abstract : This paper presents a novel direct adaptive neural network controller for switched reluctance motor (SRM) speed control, which takes into account parameter variations, external load disturbances, and input saturation constraint. The radial basis function (RBF) neural network based on the technology of minimal learning parameters (MLP) is employed to approximate an ideal control law that includes parameter variations and external disturbances. An auxiliary dynamic system is constructed to handle the input saturation constraint. Furthermore, uniform ultimate boundedness of all signals in the SRM drive closed‐loop control system is guaranteed through rigorous Lyapunov analysis. Comparative studies are carried out between the proposed control scheme and conventional proportional‐integral (PI) control, and the simulation and experimental results show that the proposed control scheme has better performance for parameter variations and external load disturbances. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.