Neural Network Control of Asymmetrical Multilevel Converters Rachid TALEB, Abdelkader MEROUFEL, Patrice WIRA Leonardo J Sci 2009; 8(15):53-70 ICID: 901004
Article type: Original article
IC™ Value: 4.48
images/publishers/1997.gif
Abstract provided by Publisher
This paper proposes a neural implementation of a harmonic elimination
strategy (HES) to control a Uniform Step Asymmetrical Multilevel Inverter
(USAMI). The mapping between the modulation rate and the required
switching angles is learned and approximated with a Multi-Layer Perceptron
(MLP) neural network. After learning, appropriate switching angles can be
determined with the neural network leading to a low-computational-cost
neural controller which is well suited for real-time applications. This
technique can be applied to multilevel inverters with any number of levels. As
an example, a nine-level inverter and an eleven-level inverter are considered
and the optimum switching angles are calculated on-line. Comparisons to the
well-known sinusoidal pulse-width modulation (SPWM) have been carried
out in order to evaluate the performance of the proposed approach. Simulation
results demonstrate the technical advantages of the proposed neural
implementation over the conventional method (SPWM) in eliminating
harmonics while controlling a nine-level and eleven-level USAMI. This
neural approach is applied for the supply of an asynchronous machine and
results show that it ensures a highest quality torque by efficiently canceling
the harmonics generated by the inverters.
Index Copernicus 2010. All rights reserved. Design by ww design
IndexCopernicus is property of Index Copernicus International S.A.. Copying information, in part or in whole by any means is prohibited without a written permission from the owner. The way of linking the service has to be agreed with the IT Department of Index Copernicus International S.A. (webmaster@indexcopernicus.com).
