A Self-Learning Solution for Torque Ripple ...
Type de document :
Article dans une revue scientifique: Article original
URL permanente :
Titre :
A Self-Learning Solution for Torque Ripple Reduction for Non-Sinusoidal Permanent Magnet Motor Drives Based on Artificial Neural Networks
Auteur(s) :
Flieller, Damien [Auteur]
Groupe de Recherche en Electrotechnique et Electronique de Nancy [GREEN]
Nguyen, Ngac Ky [Auteur]
13338|||Laboratoire d’Électrotechnique et d’Électronique de Puissance - ULR 2697 [L2EP]
WIRA, Patrick [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Sturtzer, Guy [Auteur]
Groupe de Recherche en Electrotechnique et Electronique de Nancy [GREEN]
Ould Abdeslam, Djaffar [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Merckle, Jean [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Groupe de Recherche en Electrotechnique et Electronique de Nancy [GREEN]
Nguyen, Ngac Ky [Auteur]
13338|||Laboratoire d’Électrotechnique et d’Électronique de Puissance - ULR 2697 [L2EP]
WIRA, Patrick [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Sturtzer, Guy [Auteur]
Groupe de Recherche en Electrotechnique et Electronique de Nancy [GREEN]
Ould Abdeslam, Djaffar [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Merckle, Jean [Auteur]
Modélisation, Intelligence, Processus et Système [MIPS]
Titre de la revue :
IEEE Transactions on Industrial Electronics
Numéro :
61
Pagination :
12
Éditeur :
Institute of Electrical and Electronics Engineers
Date de publication :
2013
ISSN :
0278-0046
Mot(s)-clé(s) :
Neuro-controller
Homopolar Current
Permanent Magnet Synchronous Motor
Torque Ripple
Cogging Torque
Adaline
Homopolar Current
Permanent Magnet Synchronous Motor
Torque Ripple
Cogging Torque
Adaline
Mot(s)-clé(s) en anglais :
Adaline
cogging torque
homopolar current
neurocontroller
permanent-magnet synchronous motor (PMSM)
torque ripple
cogging torque
homopolar current
neurocontroller
permanent-magnet synchronous motor (PMSM)
torque ripple
Discipline(s) HAL :
Sciences de l'ingénieur [physics]/Energie électrique
Sciences de l'ingénieur [physics]/Electromagnétisme
Physique [physics]/Matière Condensée [cond-mat]/Supraconductivité [cond-mat.supr-con]
Sciences de l'ingénieur [physics]/Electromagnétisme
Physique [physics]/Matière Condensée [cond-mat]/Supraconductivité [cond-mat.supr-con]
Résumé en anglais : [en]
This paper presents an original method, based on artificial neural networks, to reduce the torque ripple in a permanent-magnet nonsinusoidal synchronous motor. Solutions for calculating optimal currents are deduced from ...
Lire la suite >This paper presents an original method, based on artificial neural networks, to reduce the torque ripple in a permanent-magnet nonsinusoidal synchronous motor. Solutions for calculating optimal currents are deduced from geometrical considerations and without a calculation step, which is generally based on the Lagrange optimization. These optimal currents are obtained from two hyperplanes. This paper takes into account the presence of harmonics in the back-EMF and the cogging torque. New control schemes are thus proposed to derive the optimal stator currents giving exactly the desired electromagnetic torque (or speed) and minimizing the ohmic losses. The torque and the speed control scheme both integrate two neural blocks, one dedicated for optimal-current calculation and the other to ensure the generation of these currents via a voltage source inverter. Simulation and experimental results from a laboratory prototype are shown to confirm the validity of the proposed neural approach.Lire moins >
Lire la suite >This paper presents an original method, based on artificial neural networks, to reduce the torque ripple in a permanent-magnet nonsinusoidal synchronous motor. Solutions for calculating optimal currents are deduced from geometrical considerations and without a calculation step, which is generally based on the Lagrange optimization. These optimal currents are obtained from two hyperplanes. This paper takes into account the presence of harmonics in the back-EMF and the cogging torque. New control schemes are thus proposed to derive the optimal stator currents giving exactly the desired electromagnetic torque (or speed) and minimizing the ohmic losses. The torque and the speed control scheme both integrate two neural blocks, one dedicated for optimal-current calculation and the other to ensure the generation of these currents via a voltage source inverter. Simulation and experimental results from a laboratory prototype are shown to confirm the validity of the proposed neural approach.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Commentaire :
https://hal.archives-ouvertes.fr/hal-00794383v1
Équipe(s) de recherche :
Équipe Commande
Date de dépôt :
2020-05-15T14:53:32Z
2022-03-15T11:30:09Z
2022-03-15T11:30:09Z
Fichiers
- https://hal.archives-ouvertes.fr/hal-00794383/document
- Accès libre
- Accéder au document