Neuro fuzzy modeling of axial field machines behavior

A. Al-Badi, K. El-Metwally, A. Gastli

Research output: Contribution to journalArticle

Abstract

Purpose - This paper aims to study modeling of the nonlinear behavior of the Torus machine back EMF using an adaptive networks fuzzy inference system (ANFIS). The model can be used to study the steady-state as well as the dynamic performances of the machine operating as a motor or as a generator. Design/methodology/approach - Using the universal approximation capability of fuzzy systems the authors designed an ANFIS network to model the nonlinear behavior of the back EMF of the Torus motor. The ANFIS is trained using an actual set machine measurements data to generate the motor back EMF for different operating conditions. Findings - Simulation results of the ANFIS model of the Torus motor at different loads proved the ability of the algorithm to effectively model the complex electromagnetic behavior of the machine. Such efficient modeling can directly help in improving and optimizing the Torus motor drive system design. Originality/value - It demonstrates that ANFIS can model the nonlinear behavior of the back EMF of the Torus motor with excellent accuracy.

Original languageEnglish
Pages (from-to)407-417
Number of pages11
JournalCOMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering
Volume26
Issue number2
DOIs
Publication statusPublished - 2007

Keywords

  • Fuzzy control
  • Modelling
  • Neural nets
  • Simulation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Neuro fuzzy modeling of axial field machines behavior'. Together they form a unique fingerprint.

  • Cite this