毫米波E面滤波器神经网络建模方法研究  

Research on Neural Network Modeling Method to Millimeter Waves E-Plane Filter

作　　者：孙璐[1] 王家礼[1] 陈晓龙[1] 

机构地区：[1]西安电子科技大学机电工程学院,陕西西安710071

出　　处：《现代电子技术》2009年第22期132-134,共3页Modern Electronics Technique

基　　金：电子测量技术国家重点实验室资助项目(6134903)

摘　　要：在毫米波E面滤波器的设计中,对E面膜片的建模和分析是一个关键环节。以往采用的数值分析方法虽然精度较高,但建模速度慢。提出采用径向基神经网络对膜片建模,并利用Matlab语言编写神经网络建模程序。结果表明,得到了很高的建模精度,且建模速度大大提高。因此可以将神经网络模型替代以往的分析程序,在保证精度的同时,大大提高滤波器的设计速度。In the design of millimeter waves E - plane filter,it is a key part of modeling and analysis method to E - plane septum. Previously used Numerical analysis methods have good accuracy, hut slow in speed. Radial Basis Funetion（RBF） neural network is proposed to the modeling of E - plane septum and modeling procedures can be realized by the advanced programming language of Matlab. It can be verified that this modeling method is faster and has a better accuracy. Neural network model can be used to replace traditional analysis procedures,and the design speed of millimeter waves filter can be greatly improved.

关 键 词：径向基神经网络 E面膜片 建模速度 毫米波滤波器 

分 类 号：TN713[电子电信—电路与系统]