Modified LMS adaptive algorithm for CMAC neural network based control of switched reluctance motors

C. Shang, D. S. Reay, B. W. Williams

Research output: Contribution to journalArticle

Abstract

A novel approach to adapting the weights of a CMAC neural network for torque ripple reduction in switched reluctance motors is proposed, using a variable learning rate function within the standard LMS algorithm. Simulation results demonstrate that training CMAC networks following this approach affords low torque ripple with high power efficiency.

Original languageEnglish
Pages (from-to)1113-1115
Number of pages3
JournalElectronics Letters
Volume32
Issue number12
Publication statusPublished - 6 Jun 1996

Fingerprint

Reluctance motors
Adaptive algorithms
Torque
Neural networks

Keywords

  • Neurocontrollers
  • Reluctance motors

Cite this

@article{061016426981471a9bc3e8472d32a7ce,
title = "Modified LMS adaptive algorithm for CMAC neural network based control of switched reluctance motors",
abstract = "A novel approach to adapting the weights of a CMAC neural network for torque ripple reduction in switched reluctance motors is proposed, using a variable learning rate function within the standard LMS algorithm. Simulation results demonstrate that training CMAC networks following this approach affords low torque ripple with high power efficiency.",
keywords = "Neurocontrollers, Reluctance motors",
author = "C. Shang and Reay, {D. S.} and Williams, {B. W.}",
year = "1996",
month = "6",
day = "6",
language = "English",
volume = "32",
pages = "1113--1115",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "12",

}

Modified LMS adaptive algorithm for CMAC neural network based control of switched reluctance motors. / Shang, C.; Reay, D. S.; Williams, B. W.

In: Electronics Letters, Vol. 32, No. 12, 06.06.1996, p. 1113-1115.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modified LMS adaptive algorithm for CMAC neural network based control of switched reluctance motors

AU - Shang, C.

AU - Reay, D. S.

AU - Williams, B. W.

PY - 1996/6/6

Y1 - 1996/6/6

N2 - A novel approach to adapting the weights of a CMAC neural network for torque ripple reduction in switched reluctance motors is proposed, using a variable learning rate function within the standard LMS algorithm. Simulation results demonstrate that training CMAC networks following this approach affords low torque ripple with high power efficiency.

AB - A novel approach to adapting the weights of a CMAC neural network for torque ripple reduction in switched reluctance motors is proposed, using a variable learning rate function within the standard LMS algorithm. Simulation results demonstrate that training CMAC networks following this approach affords low torque ripple with high power efficiency.

KW - Neurocontrollers

KW - Reluctance motors

UR - http://www.scopus.com/inward/record.url?scp=0030572222&partnerID=8YFLogxK

M3 - Article

VL - 32

SP - 1113

EP - 1115

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 12

ER -