Model order reduction for parameterized electromagnetic problems using matrix decomposition and deep neural networks - Laboratoire Jean-Alexandre Dieudonné Accéder directement au contenu
Article Dans Une Revue Journal of Computational and Applied Mathematics Année : 2023

Model order reduction for parameterized electromagnetic problems using matrix decomposition and deep neural networks

Résumé

A non-intrusive model order reduction (MOR) method for solving parameterized electromagnetic scattering problems is proposed in this paper. A database collecting snapshots of high-fidelity solutions is built by solving the parameterized time-domain Maxwell equations for some values of the material parameters using a fullwave solver based on a high order discontinuous Galerkin time-domain (DGTD) method. To perform a prior dimensionality reduction, a set of reduced basis (RB) functions are extracted from the database via a two-step proper orthogonal decomposition (POD) method. Projection coefficients of the reduced basis functions are further compressed through a convolutional autoencoder (CAE) network. Singular value decomposition (SVD) is then used to extract the principal components of the reduced-order matrices generated by CAE, and a cubic spline interpolation-based (CSI) approach is employed for approximating the dominating time-and parameter-modes of the reduced-order matrices. The generation of the reduced basis and the training of the CAE and CSI are accomplished in the offline stage, thus the RB solution for given time/parameter values can be quickly recovered via outputs of the interpolation model and decoder network. In particular, the offline and online stages of the proposed RB method are completely decoupled, which ensures the validity of the method. The performance of the proposed CAE-CSI ROM is illustrated with numerical experiments for scattering of a plane wave by a 2-D dielectric disk and a multi-layer heterogeneous medium.
Fichier principal
Vignette du fichier
2207.07811.pdf (3.78 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03927379 , version 1 (06-01-2023)

Licence

Paternité

Identifiants

Citer

Xiao-Feng He, Liang Li, Stéphane Lanteri, Kun Li. Model order reduction for parameterized electromagnetic problems using matrix decomposition and deep neural networks. Journal of Computational and Applied Mathematics, 2023, 431, pp.115271. ⟨10.1016/j.cam.2023.115271⟩. ⟨hal-03927379⟩
24 Consultations
64 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More