Shape Modeling of Microstrip Filters Based on Convolutional Neural Network

IF 3.3 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Microwave and Wireless Components Letters Pub Date : 2022-09-01 DOI:10.1109/LMWC.2022.3162414

Hai-Ying Luo, W. Shao, Xiao Ding, Bing-Zhong Wang, Xi Cheng

引用次数: 2

Abstract

An effective convolutional neural network (CNN) with the transfer function (TF) is proposed for shape modeling of electromagnetic (EM) behaviors of microstrip filters. The input of CNN is the images of metallic strips instead of the geometric parameters. To define the training samples, a one-to-one relation between the strip contour and the knot positions is built with a shape-changing technique based on cubic spline interpolation. The proposed model is confirmed with an example of a microstrip/coplanar waveguide (CPW) ultrawideband (UWB) filter. Compared with the parametric artificial neural network (ANN) and the shape ANN, the proposed model shows the improvement of design flexibility and the expansion of the solution domain.

查看原文本刊更多论文

基于卷积神经网络的微带滤波器形状建模

提出了一种有效的带有传递函数的卷积神经网络(CNN)，用于微带滤波器电磁行为的形状建模。CNN的输入是金属条的图像，而不是几何参数。为了定义训练样本，采用基于三次样条插值的形状变化技术建立了条带轮廓与结位置之间的一一对应关系。最后以微带/共面波导(CPW)超宽带(UWB)滤波器为例进行了验证。与参数人工神经网络(ANN)和形状人工神经网络(shape ANN)相比，该模型提高了设计灵活性，扩展了求解域。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Microwave and Wireless Components Letters 工程技术-工程：电子与电气

自引率

13.30%

发文量

376

审稿时长

3.0 months

期刊介绍： The IEEE Microwave and Wireless Components Letters (MWCL) publishes four-page papers (3 pages of text + up to 1 page of references) that focus on microwave theory, techniques and applications as they relate to components, devices, circuits, biological effects, and systems involving the generation, modulation, demodulation, control, transmission, and detection of microwave signals. This includes scientific, technical, medical and industrial activities. Microwave theory and techniques relates to electromagnetic waves in the frequency range of a few MHz and a THz; other spectral regions and wave types are included within the scope of the MWCL whenever basic microwave theory and techniques can yield useful results. Generally, this occurs in the theory of wave propagation in structures with dimensions comparable to a wavelength, and in the related techniques for analysis and design.