Filter approximation by RBF-NN and segmentation method

2004 IEEE MTT-S International Microwave Symposium Digest (IEEE Cat. No.04CH37535) Pub Date : 2004-06-06 DOI:10.1109/MWSYM.2004.1338877

F. Nunez, A. Skrivervik

引用次数: 8

Abstract

In this paper, radial basis function neural networks (RBF-NN) are used to approximate microwave filters. The method used is based on the segmentation of the structure in small units and the approximation of their scattering parameters. The approximated transmission matrices of each unit are multiplied to reproduce the whole filter response. This method is applied to a genetic algorithm in order to obtain a 13 sections microwave step filter, with a specified response. The RBF-NN response of the resulting filter is compared with its full-wave method of moments analysis showing a considerable save of computation time and increased accuracy in the results.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

采用RBF-NN滤波逼近和分割方法

本文采用径向基函数神经网络(RBF-NN)逼近微波滤波器。该方法是基于小单元结构的分割和散射参数的近似。将每个单元的近似传输矩阵相乘以再现整个滤波器响应。将该方法应用于遗传算法，得到了具有特定响应的13段微波阶跃滤波器。将所得滤波器的RBF-NN响应与其全波矩分析方法进行了比较，结果显示计算时间大大节省，结果精度提高。

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分钟内获得全文去求助

来源期刊

2004 IEEE MTT-S International Microwave Symposium Digest (IEEE Cat. No.04CH37535)

自引率

0.00%

发文量

期刊最新文献

Effect of laser and RF oscillator phase noises New high-accuracy subgridding technique for the method of lines Low loss coupled line filters with transmission zeros in multi-layer thin film MCM-D technology Highly efficient power amplifier for CDMA base stations using Doherty configuration A V-band VCO and frequency divider MMICs for phased-locked loop