Current controller for induction motor using an Artificial Neural Network trained with a Lyapunov based algorithm

Julio Viola, Jose Restrepo, Jose Aller

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución de conferenciarevisión exhaustiva

Resumen

This paper presents the use of a training algorithm based on a Lyapunov function approach applied to a stator current controller based on a state variable description of the induction machine plus a reference model. The results obtained with the proposed controller are compared with a previously reported method based on a Nonlinear Auto-Regressive Moving Average with eXogenous inputs (NARMAX) description of the induction machine. The proposed Lyapunov based training algorithm is used to ensure convergence of the weights towards a global minimum in the error function. Real time simulations employing a DSP based test bench are used to test the validity of the algorithms and the results are verified by a practical implementation of these controllers.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2015 IEEE 24th International Symposium on Industrial Electronics, ISIE 2015
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas468-475
Número de páginas8
ISBN (versión digital)9781467375542
DOI
EstadoPublicada - 28 sep. 2015
Evento24th IEEE International Symposium on Industrial Electronics, ISIE 2015 - Buzios, Rio de Janeiro, Brasil
Duración: 3 jun. 20155 jun. 2015

Serie de la publicación

NombreIEEE International Symposium on Industrial Electronics
Volumen2015-September

Conferencia

Conferencia24th IEEE International Symposium on Industrial Electronics, ISIE 2015
País/TerritorioBrasil
CiudadBuzios, Rio de Janeiro
Período3/06/155/06/15

Nota bibliográfica

Publisher Copyright:
© 2015 IEEE.

Huella

Profundice en los temas de investigación de 'Current controller for induction motor using an Artificial Neural Network trained with a Lyapunov based algorithm'. En conjunto forman una huella única.

Citar esto