Two-Dimensional Electromagnetic Solver Based on Deep Learning Technique
- 19 May 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Multiscale and Multiphysics Computational Techniques
- Vol. 5, 83-88
Abstract
Although the deep learning (DL) technique has been introduced into computational physics in recent years, the feasibility of applying it to solve electromagnetic (EM) scattering field from arbitrary scatters remains open. In this paper, the convolutional neural network (CNN) has been employed to predict the EM field scattered by complex geometries under plane wave illumination. The 2D finite difference frequency domain (FDFD) algorithm, wrapped by a module to randomly generate complex scatters from basic geometries, is employed to produce training data for the network. The multi-channel end-to-end CNN U-net is modified and combined with a Resnet, which can prevent the vanishing gradient problem in the training process, to form the EM-net. The well-trained EM-net has good performance in this problem since it is compatible with various of complex shapes, multiple kinds of materials and different propagation directions of the incident waves. The effectiveness of the proposed EM-net has been validated by numerical experiments, and the average numerical error can be as small as 1.02%. Meanwhile, its speedup ratio over the FDFD method is as large as 2000.Keywords
Funding Information
- National Natural Science Foundation of China (61801009, 61871063)
- 13th Five-Year Equipment Pre-Research (61402090603, 61402080205)
This publication has 20 references indexed in Scilit:
- Study on a Poisson's equation solver based on deep learning technique2017
- Cognitive foundations of knowledge science and deep knowledge learning by cognitive robots2017
- Machine learning based method of moments (ML-MoM)2017
- Convolutional Neural Networks for Steady Flow Approximation2016
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Recent computational developments in Krylov subspace methods for linear systemsNumerical Linear Algebra with Applications, 2006
- Field Computation by Moment Methods1993
- Methods of conjugate gradients for solving linear systemsJournal of Research of the National Bureau of Standards, 1952