Titre : | Implémentation en temps réel d’une technique d’analyse spectrale paramétrique à l’aide de l’approche neuro-floue optimisée par les algorithmes génétiques |
Auteurs : | Mohamed Ouarem ; Fateh Krim, Directeur de thèse |
Type de document : | texte imprimé |
Editeur : | Sétif : Université Ferhat Abbas faculté de technologie département d’électronique |
ISBN/ISSN/EAN : | TS4/7469 |
Format : | 1 vol. (76 f.) / ill. Tableaux |
Note générale : | Bibliogr. |
Langues: | Anglais |
Catégories : | |
Résumé : |
Real-time harmonics monitoring has become a major concern in many applications, as in electrical power systems which are experienced to harmonic distortion due to non-linear loads. The time limitations and computational complexity associated with conventional techniques make it appealing to investigate alternative techniques for harmonic extraction. From another hand, almost applications, such as filter design, need techniques for the fast extraction of individual harmonic components. Therefore, a technique based on fuzzy neural networks optimized by genetic algorithms for the fast extraction of individual harmonic components is presented here. It uses a type of fusion between artificial neural network and fuzzy logic control whose membership functions are adjusted suitably, due to the artificial neural network learning ability, to accurately estimate, on-line, the individual harmonic components of a distorted signal. The proposed technique is realized and simulated. Results show that the proposed technique is significantly faster and accurate than conventional techniques. |
Exemplaires (1)
Cote | Support | Localisation | Disponibilité |
---|---|---|---|
TS4/7469 | Thèse | Bibliothèque centrale | Disponible |
Accueil