Further investigation of convolutional ...
Type de document :
Article dans une revue scientifique: Article original
DOI :
URL permanente :
Titre :
Further investigation of convolutional neural networks applied in computational electromagnetism under physics‐informed consideration
Auteur(s) :
Gong, Ruohan [Auteur]
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Tang, Zuqi [Auteur correspondant]
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Tang, Zuqi [Auteur correspondant]
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Titre de la revue :
IET Electric Power Applications
Nom court de la revue :
IET Electric Power Appl
Numéro :
16
Pagination :
653-674
Éditeur :
Institution of Engineering and Technology (IET)
Date de publication :
2022-04-07
ISSN :
1751-8660
Discipline(s) HAL :
Sciences de l'ingénieur [physics]
Résumé en anglais : [en]
Convolutional neural networks (CNN) have shown great potentials and have been proven to be an effective tool for some image-based deep learning tasks in the field of computational electromagnetism (CEM). In this work, an ...
Lire la suite >Convolutional neural networks (CNN) have shown great potentials and have been proven to be an effective tool for some image-based deep learning tasks in the field of computational electromagnetism (CEM). In this work, an energy-based physics-informed neural network (EPINN) is proposed for low-frequency electromagnetic computation. Two different physics-informed loss functions are designed. To help the network focus on the region of interest instead of computing the whole domain on average, the magnetic energy norm error loss function is proposed. Besides, the methodology of energy minimization is integrated into the CNN by introducing the magnetic energy error loss function. It is observed that the introduction of the physics-informed loss functions improved the accuracy of the network with the same architecture and database. Meanwhile, these changes also cause the network to be more sensitive to some hyperparameters and makes the training process oscillate or even diverge. To address this issue, the sensitivity of the network hyperparameters for both physics-informed loss functions are further investigated. Numerical experiments demonstrate that the proposed approaches have good accuracy and efficiency with fine-tuned hyperparameters. Furthermore, the post-test illustrates that the EPINN has excellent interpolation performance and can obtain good extrapolation results under certain restrictions.Lire moins >
Lire la suite >Convolutional neural networks (CNN) have shown great potentials and have been proven to be an effective tool for some image-based deep learning tasks in the field of computational electromagnetism (CEM). In this work, an energy-based physics-informed neural network (EPINN) is proposed for low-frequency electromagnetic computation. Two different physics-informed loss functions are designed. To help the network focus on the region of interest instead of computing the whole domain on average, the magnetic energy norm error loss function is proposed. Besides, the methodology of energy minimization is integrated into the CNN by introducing the magnetic energy error loss function. It is observed that the introduction of the physics-informed loss functions improved the accuracy of the network with the same architecture and database. Meanwhile, these changes also cause the network to be more sensitive to some hyperparameters and makes the training process oscillate or even diverge. To address this issue, the sensitivity of the network hyperparameters for both physics-informed loss functions are further investigated. Numerical experiments demonstrate that the proposed approaches have good accuracy and efficiency with fine-tuned hyperparameters. Furthermore, the post-test illustrates that the EPINN has excellent interpolation performance and can obtain good extrapolation results under certain restrictions.Lire moins >
Langue :
Anglais
Audience :
Internationale
Vulgarisation :
Non
Établissement(s) :
Université de Lille
Centrale Lille
Arts et Métiers Sciences et Technologies
Junia HEI
Centrale Lille
Arts et Métiers Sciences et Technologies
Junia HEI
Équipe(s) de recherche :
Équipe Outils et Méthodes Numériques
Date de dépôt :
2023-01-25T00:20:35Z
2023-01-26T10:18:01Z
2023-01-26T10:18:01Z
Fichiers
- GONG_TANG_IET.pdf
- Version éditeur
- Accès libre
- Accéder au document