基于resnet的人工电磁材料深度学习设计

IF 1.1 4区 计算机科学 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC
Yu Xie, Yi Wang, Songran Guo
{"title":"基于resnet的人工电磁材料深度学习设计","authors":"Yu Xie,&nbsp;Yi Wang,&nbsp;Songran Guo","doi":"10.1049/mia2.70007","DOIUrl":null,"url":null,"abstract":"<p>The design of artificial electromagnetic materials (AEMMs) depends highly on full-wave numerical simulations or equivalent circuit model (ECM)-assisted analysis. This work proposes an intelligent design method using a deep learning (DL) technique based on the residual neural network (ResNet) to improve its efficiency. Firstly, adopting pixeled matrix modelling methods enhances the freedom of design. Next, the staircase approximation is utilised for the S-parameter curve, which also describes the required electromagnetic (EM) property to be used in the training process. These processed samples, along with their corresponding labels, are transformed and fed into ResNet for training. After these procedures, the structural matrix of the desired curve can be predicted through well-trained networks. To validate the effectiveness of the method, typical notched-band frequency selective absorbers (FSAs) are designed, while the reflective band can easily be adjusted. Compared with conventional methods and other deep neural network (DNN)-based methods, this method performs more efficiently and accurately. Finally, an illustrative sample is fabricated to validate the prediction result.</p>","PeriodicalId":13374,"journal":{"name":"Iet Microwaves Antennas & Propagation","volume":"19 1","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/mia2.70007","citationCount":"0","resultStr":"{\"title\":\"Design of Artificial Electromagnetic Materials Using ResNet-Based Deep Learning Method\",\"authors\":\"Yu Xie,&nbsp;Yi Wang,&nbsp;Songran Guo\",\"doi\":\"10.1049/mia2.70007\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The design of artificial electromagnetic materials (AEMMs) depends highly on full-wave numerical simulations or equivalent circuit model (ECM)-assisted analysis. This work proposes an intelligent design method using a deep learning (DL) technique based on the residual neural network (ResNet) to improve its efficiency. Firstly, adopting pixeled matrix modelling methods enhances the freedom of design. Next, the staircase approximation is utilised for the S-parameter curve, which also describes the required electromagnetic (EM) property to be used in the training process. These processed samples, along with their corresponding labels, are transformed and fed into ResNet for training. After these procedures, the structural matrix of the desired curve can be predicted through well-trained networks. To validate the effectiveness of the method, typical notched-band frequency selective absorbers (FSAs) are designed, while the reflective band can easily be adjusted. Compared with conventional methods and other deep neural network (DNN)-based methods, this method performs more efficiently and accurately. Finally, an illustrative sample is fabricated to validate the prediction result.</p>\",\"PeriodicalId\":13374,\"journal\":{\"name\":\"Iet Microwaves Antennas & Propagation\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2025-03-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/mia2.70007\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iet Microwaves Antennas & Propagation\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/mia2.70007\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Microwaves Antennas & Propagation","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/mia2.70007","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

人工电磁材料的设计在很大程度上依赖于全波数值模拟或等效电路模型(ECM)辅助分析。本文提出了一种基于残差神经网络(ResNet)的深度学习(DL)技术的智能设计方法,以提高其效率。首先,采用像素化矩阵建模方法,提高了设计的自由度。接下来,阶梯近似用于s参数曲线,该曲线还描述了在训练过程中使用的所需电磁(EM)特性。这些经过处理的样本,连同它们对应的标签,被转换并输入ResNet进行训练。经过这些步骤,期望曲线的结构矩阵可以通过训练良好的网络来预测。为了验证该方法的有效性,设计了典型的陷波带频率选择吸收器(FSAs),其反射带易于调节。与传统方法和其他基于深度神经网络(DNN)的方法相比,该方法具有更高的效率和准确性。最后,制作了一个说明性样本来验证预测结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Design of Artificial Electromagnetic Materials Using ResNet-Based Deep Learning Method

Design of Artificial Electromagnetic Materials Using ResNet-Based Deep Learning Method

The design of artificial electromagnetic materials (AEMMs) depends highly on full-wave numerical simulations or equivalent circuit model (ECM)-assisted analysis. This work proposes an intelligent design method using a deep learning (DL) technique based on the residual neural network (ResNet) to improve its efficiency. Firstly, adopting pixeled matrix modelling methods enhances the freedom of design. Next, the staircase approximation is utilised for the S-parameter curve, which also describes the required electromagnetic (EM) property to be used in the training process. These processed samples, along with their corresponding labels, are transformed and fed into ResNet for training. After these procedures, the structural matrix of the desired curve can be predicted through well-trained networks. To validate the effectiveness of the method, typical notched-band frequency selective absorbers (FSAs) are designed, while the reflective band can easily be adjusted. Compared with conventional methods and other deep neural network (DNN)-based methods, this method performs more efficiently and accurately. Finally, an illustrative sample is fabricated to validate the prediction result.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Iet Microwaves Antennas & Propagation
Iet Microwaves Antennas & Propagation 工程技术-电信学
CiteScore
4.30
自引率
5.90%
发文量
109
审稿时长
7 months
期刊介绍: Topics include, but are not limited to: Microwave circuits including RF, microwave and millimetre-wave amplifiers, oscillators, switches, mixers and other components implemented in monolithic, hybrid, multi-chip module and other technologies. Papers on passive components may describe transmission-line and waveguide components, including filters, multiplexers, resonators, ferrite and garnet devices. For applications, papers can describe microwave sub-systems for use in communications, radar, aerospace, instrumentation, industrial and medical applications. Microwave linear and non-linear measurement techniques. Antenna topics including designed and prototyped antennas for operation at all frequencies; multiband antennas, antenna measurement techniques and systems, antenna analysis and design, aperture antenna arrays, adaptive antennas, printed and wire antennas, microstrip, reconfigurable, conformal and integrated antennas. Computational electromagnetics and synthesis of antenna structures including phased arrays and antenna design algorithms. Radiowave propagation at all frequencies and environments. Current Special Issue. Call for papers: Metrology for 5G Technologies - https://digital-library.theiet.org/files/IET_MAP_CFP_M5GT_SI2.pdf
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信