电子测量与仪器学报

南敬昌,孙雯雯,杜有益,王明寰.一维卷积神经网络超宽带天线建模方法[J].电子测量与仪器学报,2023,37(2):204-210

一维卷积神经网络超宽带天线建模方法

One-dimensional convolutional neural network modeling method for ultra-wideband antenna

DOI：

中文关键词: 一维卷积神经网络超宽带单极子天线 Adam 优化器 dropout 技术

英文关键词:one-dimensional convolutional neural network the UWB monopole antenna Adam optimizer dropout technology

基金项目:国家自然科学基金(61971210)、企业合作课题:射频 LDMOS 功放器件研究测试(21-2-32)项目资助

作者	单位
南敬昌	1. 辽宁工程技术大学电子与信息工程学院
孙雯雯	1. 辽宁工程技术大学电子与信息工程学院
杜有益	1. 辽宁工程技术大学电子与信息工程学院
王明寰	2. 南京理工大学电子工程与光电技术学院

Author	Institution
Nan Jingchang	1. School of Electronics and Information Engineering, Liaoning Technical University
Sun Wenwen	1. School of Electronics and Information Engineering, Liaoning Technical University
Du Youyi	1. School of Electronics and Information Engineering, Liaoning Technical University
Wang Minghuan	2. School of Electronic Engineering and Photoelectric Technology, Nanjing University of Science and Technology

摘要点击次数: 793

全文下载次数: 994

中文摘要:

为加快天线建模优化速度,提出了一种改进的一维卷积神经网络(1D-MCNN)模型。此一维神经网络的卷积核大小为 2,将 ReLU 函数作为激活函数降低梯度弥散;利用 Adam 优化器与 dropout 技术结合,提高模型的特征学习能力和非线性函数逼近能力。本文使用 1D-MCNN 模型对超宽带微带单极子天线几何参数建模,以天线的 8 个几何参数作为特征输入,对天线的回波损耗值进行预测。实验表明,本文所提 1D-MCNN 模型与深层 MLP 网络模型、MLP 网络模型、RBF 神经网络模型相比,回波损耗值的平均误差分别减小了 1. 95%,120. 27%,125. 71%,拥有更高的准确度,预测能力更强,对优化超宽带天线建模可行且性能具有一定优越性。

英文摘要:

To speed up the optimization of antenna modeling, an improved one-dimensional convolutional neural network ( 1D-MCNN ) model is proposed. The convolution kernel size of this one-dimensional neural network is 2, and the ReLU function is used as the activation function to reduce the gradient dispersion. The Adam optimizer is combined with dropout technology to improve the feature learning ability and nonlinear function approximation ability of the model. In this paper, the 1D-MCNN model is used to model the geometric parameters of the ultra-wideband microstrip monopole antenna. The eight geometric parameters of the antenna are used as feature inputs to predict the return loss value of the antenna. Experiments show that compared with the deep MLP network model, MLP network model, and RBF neural network model, the average error of the return loss value of the 1D-MCNN model proposed in this paper is reduced by 1. 95%, 120. 27%, and 125. 71% respectively. It has higher accuracy and stronger prediction ability. It is feasible to optimize the modeling of ultra-wideband antennas and has certain advantages.

查看全文查看/发表评论下载PDF阅读器