Physics-Informed Neural Networks with Hard Constraints for Electromagnetic Scattering Analysis
In this paper, we present a novel approach to solving two-dimensional electromagnetic scattering problem using physical-informed neural networks (PINN) enhanced with hard constraints. The proposed method is implemented under the partial differential equations (PDEs) framework, which demonstrates superior accuracy over traditional PINN structure compared to conventional numerical methods.
Authors
- Xin‐Qing Sheng (ORCID: https://orcid.org/0000-0002-8136-3705)
- Hang Li (ORCID: https://orcid.org/0000-0001-8904-4859)
- Jingang Liu (ORCID: https://orcid.org/0000-0001-6629-1646)
- Xiaowei Huang (ORCID: https://orcid.org/0000-0002-8738-0864)
Institutions
- Beijing Institute of Technology (CN)
Publication Details
- Published
- 2024-10-23
- DOI
- https://doi.org/10.1109/isape62431.2024.10841206
- Citations
- 1
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.35
Funders
- National Natural Science Foundation of China
- National Key Research and Development Program of China