Commutating switched reluctance motors efficiently via CMAC neural network with learning rate function

Changjing Shang, Donald S. Reay, Barry W. Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents a novel control scheme for torque ripple reduction in switched reluctance motors (SRMs) operating at low constant speeds. The control scheme is implemented using a CMAC neural network, trained with a modified LMS algorithm. This algorithm uses a varying learning rate function (LRF) which is defined as a function of the rotor angle of the motor under control. Experimental measurements of the static torque production of a 4 kW, four-phase SRM form the basis of simulation studies of this approach. The simulation results demonstrate that a learned current profile, capable of minimizing torque ripple while having high power efficiency, can be obtained by selecting a LRF with suitable turn-on and turn-off angles during the training of the network.

Original languageEnglish
Title of host publicationProceedings of the 1997 American Control Conference. Part 3 (of 6)
Pages237-241
Number of pages5
Volume1
Publication statusPublished - 1997
Event1997 American Control Conference - Albuquerque, NM, USA
Duration: 4 Jun 19976 Jun 1997

Conference

Conference1997 American Control Conference
CityAlbuquerque, NM, USA
Period4/06/976/06/97

Fingerprint Dive into the research topics of 'Commutating switched reluctance motors efficiently via CMAC neural network with learning rate function'. Together they form a unique fingerprint.

  • Cite this

    Shang, C., Reay, D. S., & Williams, B. W. (1997). Commutating switched reluctance motors efficiently via CMAC neural network with learning rate function. In Proceedings of the 1997 American Control Conference. Part 3 (of 6) (Vol. 1, pp. 237-241)