1. Bouira University Digital Space
2. Thèses Doctorat
3. Faculté des Sciences et des Sciences Appliquées

Titre:	Contribution à la modélisation et au diagnostic des systèmes de production d’énergie électrique à base d’énergies renouvelables
Auteur(s):	dilmi, ali
Mots-clés:	Wind Turbines ; Self-Excited Induction Generator (SEIG) ; Neural Networks (NN) ; Machine Learning and Deep Learning ; Finite Element Method (FEM) ; Fault Diagnosis ; Efficiency Improvement ; Artificial Intelligence
Date de publication:	2026
Editeur:	Université de BOUIRA جامعة البويرة
Référence bibliographique:	This thesis Addresses diagnostic approaches for wind energy conversion systems (WECSs) under both normal operating conditions and fault scenarios. The main objective is to develop an accurate modeling approach that integrates the mechanical and physical characteristics with the electromagnetic phenomena of the generator, while analyzing its performance during both intact and faulty scenarios. Furthermore, it aims to design effective diagnostic strategies capable of detecting and classifying faults with high accuracy. The study is based on a 4.087 MW Self-Excited Induction Generator (SEIG) and employs the Finite Element Method (FEM) to achieve advanced modeling. In addition, the thesis investigates the application of machine learning and deep learning techniques as modern tools for intelligent fault diagnosis. Overall, this research contributes to the advancement of renewable energy technologies and the enhancement of their efficiency by combining advanced mechanical–physical modeling with state-of-the-art artificial intelligence algorithms.
URI/URL:	http://dspace.univ-bouira.dz:8080/jspui/handle/123456789/20028
Collection(s) :	Faculté des Sciences et des Sciences Appliquées

Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.