By Topic

Rotor time constant adaptation using Radial Basis Function network

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
BrandsĖŒtetter, P. ; VSB - Tech. Univ. of Ostrava, Ostrava-Poruba ; Skuta, O.

Our intention here was to highlight a replacement of adaptation algorithm in MRAS by the help of alternative artificial neural network (ANN) which has received great attention in recent years. The main objective was to find and design some alternative neural network within the electric drive control. After a short discussion of hardware components, an overview of radial basis function (RBF) neural networks will be given. Digital signal processors TMS320F2812 are used for these electric drives control applications. The hardware accessories used within the electric control drive included: interface board for the signal processor kit-developed in our department, and an 8 bit data-transfer microprocessor for data acquisition. The interface of the DSP is a general-purpose control system for power converters in the electric drives. The next section briefly outlines the estimation of the rotor time constant, which is necessary for the so-called current model. The current model is used in the vector control of the induction motor and is utilized to determine the quantities for the transformation from the stationary reference frame into the reference frame, which is oriented on the rotor flux space vector. The estimation of the rotor time constant for the adaptive model of MRAS is created with the support of a PI-controller which is then replaced with the radial basis function network. The final section presents simulations results, which have been performed in the Matlab-Simulink software.

Published in:

Power Electronics and Motion Control Conference, 2008. EPE-PEMC 2008. 13th

Date of Conference:

1-3 Sept. 2008