Equivalent Electromagnetic Parameter Inversion of Honeycomb Structures Based on BP Neural Network

Yu Xin Zhang*, Xiao Wei Yuan, Ming Lin Yang*, Xin Qing Sheng

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We present in this paper an effective BP neural network-based method for the equivalent electromagnetic parameter inversion of honeycomb structures. The BP neural network is trained using radar cross section (RCS) of different honeycomb structures and the equivalent dielectric constants of the honeycomb as the input and output variables, respectively. To simplify the sample data generation and reduce the dimension of output variables, the Hashin-Shtrikman (HS) variational theory is used to homogenize the honeycomb structure as homogenous materials. The hybrid finite element-boundary integral-multilevel fast multipole method (FE-BI-MLFMA) is used as the solver for scattering problems after homogenization. Numerical results show that the trained high-quality network model can achieve good accuracy, which provides an effective way for predicting equivalent electromagnetic parameter of microwave absorbing honeycomb structures.

源语言英语
主期刊名2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781665452366
DOI
出版状态已出版 - 2022
活动2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022 - Xuzhou, 中国
期限: 9 12月 202212 12月 2022

出版系列

姓名2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

会议

会议2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022
国家/地区中国
Xuzhou
时期9/12/2212/12/22

指纹

探究 'Equivalent Electromagnetic Parameter Inversion of Honeycomb Structures Based on BP Neural Network' 的科研主题。它们共同构成独一无二的指纹。

引用此