Amélioration des performances de régulation d’une machine asynchrone à double alimentation par la technique Neuro-flou

Abstract

Ce mémoire présente l’amélioration des performances de régulation de la Machine Asynchrone à Double Alimentation.. Nous avons abordé la commande vectorielle de la MADA par orientation du flux statorique par d’autres régulateurs basés sur les techniques de l’intelligence artificielle tels que les régulateurs flous, et le neuro-flou. Les résultats de simulations et des tests de robustesse seront présentés. Abstract: In this thesis, an intelligent artificial control of a doubly fed asynchronous machine is proposed. First, a mathematical model of DFAM written in an appropriate d-q reference frame is established to investigate simulations results. In order to control the speed of rotor; Then an intelligent artificial control such as fuzzy logic and Neuro-fuzzy control are applied. Its simulated performances are then compared to those of a classical PI controller. Specifically Neuro-fuzzy mechanism system is created to overcome the disadvantages of neural networks and fuzzy systems results obtained.

In this thesis, an intelligent artificial control of a doubly fed asynchronous machine is proposed. First, a mathematical model of DFAM written in an appropriate d-q reference frame is established to investigate simulations results. In order to control the speed of rotor; Then an intelligent artificial control such as fuzzy logic and Neuro-fuzzy control are applied. Its simulated performances are then compared to those of a classical PI controller. Specifically Neuro-fuzzy mechanism system is created to overcome the disadvantages of neural networks and fuzzy systems results obtained