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
  • [41] Physics-informed neural networks for gravity currents reconstruction from limited data
    Delcey, Mickael
    Cheny, Yoann
    de Richter, Sebastien Kiesgen
    PHYSICS OF FLUIDS, 2023, 35 (02)
  • [42] Physics-informed neural networks for modelling power transformer's dynamic thermal behaviour
    Bragone, Federica
    Morozovska, Kateryna
    Hilber, Patrik
    Laneryd, Tor
    Luvisotto, Michele
    Electric Power Systems Research, 2022, 211
  • [43] Physics-informed neural networks for modelling power transformer?s dynamic thermal behaviour
    Bragone, Federica
    Morozovska, Kateryna
    Hilber, Patrik
    Laneryd, Tor
    Luvisotto, Michele
    ELECTRIC POWER SYSTEMS RESEARCH, 2022, 211
  • [44] Data-driven physics-informed neural networks: A digital twin perspective
    Yang, Sunwoong
    Kim, Hojin
    Hong, Yoonpyo
    Yee, Kwanjung
    Maulik, Romit
    Kang, Namwoo
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 428
  • [45] PHYSICS-INFORMED DATA AUGMENTATION OF EXPERIMENTAL EROSION DATA THROUGH GENERATIVE ADVERSARIAL NETWORKS
    Zhang, Jun
    Li, Jamie
    Pei, Weiping
    Shirazi, Siamack
    PROCEEDINGS OF ASME 2024 FLUIDS ENGINEERING DIVISION SUMMER MEETING, VOL 2, FEDSM 2024, 2024,
  • [46] Efficient Uncertainty Quantification in Electromagnetic Modeling Using Physics-Informed Deep Operator Neural Networks
    Qi, Shutong
    Sarris, Costas D.
    2024 IEEE INC-USNC-URSI RADIO SCIENCE MEETING (JOINT WITH AP-S SYMPOSIUM), 2024, : 159 - 159
  • [47] Coupling physics-informed neural networks and constitutive relation error concept to solve a parameter identification problem
    Wei, Y.
    Serra, Q.
    Lubineau, G.
    Florentin, E.
    COMPUTERS & STRUCTURES, 2023, 283
  • [48] New insights into experimental stratified flows obtained through physics-informed neural networks
    Zhu, Lu
    Jiang, Xianyang
    Lefauve, Adrien
    Kerswell, Rich R.
    Linden, P. F.
    JOURNAL OF FLUID MECHANICS, 2024, 981
  • [49] Physics-informed neural networks for data-free surrogate modelling and engineering optimization - An example from composite manufacturing
    Wuerth, Tobias
    Krauss, Constantin
    Zimmerling, Clemens
    Kaerger, Luise
    MATERIALS & DESIGN, 2023, 231
  • [50] Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems
    Jagtap, Ameya D.
    Kharazmi, Ehsan
    Karniadakis, George Em
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2020, 365