Physics-informed neural networks for modelling anisotropic and bi-anisotropic electromagnetic constitutive laws through indirect data

被引:3
|
作者
Chandra, Abhishek [1 ]
Curti, Mitrofan [1 ]
Tiels, Koen [2 ]
Lomonova, Elena A. [1 ]
Tartakovsky, Daniel M. [3 ]
机构
[1] Eindhoven Univ Technol, Dept Elect Engn, Eindhoven, Netherlands
[2] Eindhoven Univ Technol, Dept Mech Engn, Eindhoven, Netherlands
[3] Stanford Univ, Dept Energy Resources Engn, Stanford, CA USA
来源
2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) | 2022年
关键词
PINNs; constitutive laws; electromagnetism; indirect data; anisotropic; bi-anisotropic; EQUATIONS;
D O I
10.1109/SSCI51031.2022.10022292
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper investigates the application of PhysicsInformed Neural Networks (PINNs) in modelling constitutive laws for transverse electromagnetic polarized waves in all three space dimensions governed by Maxwell Faraday equation and Ampere's circuital law. The constitutive relationships for electrical permittivity and conductivity are modelled for the 1D case. In 2D, constitutive laws for electric displacement and polarization fields are modelled for anisotropic materials without using the data for either of the two fields. Constitutive laws for bi-anisotropic media are modelled in 3D, where the electromagnetic fields are coupled. It is observed that using PDEs as a guiding constraint regularizes the learning procedure efficiently for training the neural network when no direct measurements of the functions of interest are available. Furthermore, the presented method outperforms the state-of-the-art Gaussian process regression and data-driven deep neural network in the presence of sparse indirect noisy measurement data. For all the numerical experiments, the presented method solves the forward problem simultaneously modelling the constitutive law.
引用
收藏
页码:1451 / 1459
页数:9
相关论文
共 50 条
  • [1] On the Monotonicity and Positivity of Physics-Informed Neural Networks for Highly Anisotropic Diffusion Equations
    Zhang, Wenjuan
    Al Kobaisi, Mohammed
    ENERGIES, 2022, 15 (18)
  • [2] Modelling of periodic electromagnetic structures - bi-anisotropic materials with memory.
    Bossavit, A
    Griso, G
    Miara, B
    COMPTES RENDUS MATHEMATIQUE, 2004, 338 (01) : 97 - 102
  • [3] Physics-informed constitutive modelling of hydrated biopolymer aerogel networks
    Kulcu, Ismail Dogan
    Rege, Ameya
    SOFT MATTER, 2021, 17 (21) : 5278 - 5283
  • [4] Physics-Informed Neural Networks for Inverse Electromagnetic Problems
    Baldan, Marco
    Di Barba, Paolo
    Lowther, David A.
    TWENTIETH BIENNIAL IEEE CONFERENCE ON ELECTROMAGNETIC FIELD COMPUTATION (IEEE CEFC 2022), 2022,
  • [5] Physics-Informed Neural Networks for Inverse Electromagnetic Problems
    Baldan, Marco
    Di Barba, Paolo
    Lowther, David A.
    IEEE TRANSACTIONS ON MAGNETICS, 2023, 59 (05)
  • [6] Physics-Informed Deep Neural Networks for Transient Electromagnetic Analysis
    Noakoasteen, Oameed
    Wang, Shu
    Peng, Zhen
    Christodoulou, Christos
    IEEE OPEN JOURNAL OF ANTENNAS AND PROPAGATION, 2020, 1 (01): : 404 - 412
  • [7] Physics-Informed Neural Networks with Data and Equation Scaling for Time Domain Electromagnetic Fields
    Fujita, Kazuhiro
    2022 ASIA-PACIFIC MICROWAVE CONFERENCE (APMC), 2022, : 623 - 625
  • [8] On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
    Fuhg, Jan N.
    Bouklas, Nikolaos
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2022, 394
  • [9] Electromagnetic-Thermal Analysis With FDTD and Physics-Informed Neural Networks
    Qi, Shutong
    Sarris, Costas D. D.
    IEEE JOURNAL ON MULTISCALE AND MULTIPHYSICS COMPUTATIONAL TECHNIQUES, 2023, 8 : 49 - 59
  • [10] Enhanced physics-informed neural networks for efficient modelling of hydrodynamics in river networks
    Luo, Xiao
    Yuan, Saiyu
    Tang, Hongwu
    Xu, Dong
    Ran, Qihua
    Cen, Yuhao
    Liang, Dongfang
    HYDROLOGICAL PROCESSES, 2024, 38 (04)