Estimation of speed, armature temperature, and resistance in brushed DC machines using a CFNN based on BFGS BP

Authors

HACENE MELLAH
KAMEL EDDINE HEMSAS
RACHID TALEB
CARLO CECATI

DOI

10.3906/elk-1711-330

Abstract

In this paper, a sensorless speed and armature resistance and temperature estimator for brushed (B) DC machines is proposed, based on a cascade-forward neural network and quasi-Newton BFGS backpropagation. Since we wish to avoid the use of a thermal sensor, a thermal model is needed to estimate the temperature of the BDC machine. Previous studies propose either nonintelligent estimators that depend on the model, such as the extended Kalman filter and Luenberger's observer, or estimators that do not estimate the speed, temperature, and resistance simultaneously. The proposed method has been verified both by simulation and by comparison with the simulation results available in the literature.

Keywords

Cascade-forward neural network, parameter estimation, quasi-Newton BFGS, speed estimation, temperature estimation, resistance estimation

First Page

3181

Last Page

3191

Recommended Citation

MELLAH, HACENE; HEMSAS, KAMEL EDDINE; TALEB, RACHID; and CECATI, CARLO (2018) "Estimation of speed, armature temperature, and resistance in brushed DC machines using a CFNN based on BFGS BP," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 26: No. 6, Article 32. https://doi.org/10.3906/elk-1711-330
Available at: https://journals.tubitak.gov.tr/elektrik/vol26/iss6/32