A Maxwell's Equations Based Deep Learning Method for Time Domain Electromagnetic Simulations

• Published in: IEEE journal on multiscale and multiphysics computational techniques Vol. 6; pp. 35 - 40
• Main Authors: Zhang, Pan, Hu, Yanyan, Jin, Yuchen, Deng, Shaogui, Wu, Xuqing, Chen, Jiefu
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Biological neural networks; Boundary conditions; Computational electromagnetics; Deep learning; Electromagnetic fields; Electromagnetics; Electromagnetism; Exact solutions; Finite difference method; Initial conditions; Interpolation; Mathematical model; Maxwell equations; Maxwell's equations; Neural networks; Numerical models; Optimization; Simulation; Time domain analysis; time domain simulations

In this paper, we discuss an unsupervised deep learning (DL) method for solving time domain electromagnetic simulations. Compared to the conventional approach, our method encodes initial conditions, boundary conditions as well as Maxwell's equations as the constraints when training the network,...