Skip to main navigation Skip to search Skip to main content

An efficient modeling technique for RF MEMS phase shifter based on RBF neural network

  • School of Electronics and Information Engineering, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A modeling technique based on RBF neural network is presented for the design of RF MEMS phase shifter. Three sensitive parameters are selected according to complicated three-dimensional structure design of an RF MEMS phase shifter and used as inputs of neural network. Experiments show that the proposed approach in this paper is a high efficiency modeling for the RF characteristics analysis for RF MEMS phase shifter. The training of the RBF neural network is accomplished within 30 minutes using 27*51 samples. The trained RBF neural network is able to predict the outputs for 51 test samples within 1 minute. Comparison between RBF neural network predictions and HFSS simulations show that the root mean square relatively errors, mean absolute relatively errors and maximize absolute relatively errors are less than 0.0368, 0.0417 and 0.0442 respectively.

Original languageEnglish
Title of host publication2008 International Conference on Microwave and Millimeter Wave Technology Proceedings, ICMMT
Pages475-478
Number of pages4
DOIs
StatePublished - 2008
Externally publishedYes
Event2008 International Conference on Microwave and Millimeter Wave Technology, ICMMT - Nanjing, China
Duration: 21 Apr 200824 Apr 2008

Publication series

Name2008 International Conference on Microwave and Millimeter Wave Technology Proceedings, ICMMT
Volume2

Conference

Conference2008 International Conference on Microwave and Millimeter Wave Technology, ICMMT
Country/TerritoryChina
CityNanjing
Period21/04/0824/04/08

Fingerprint

Dive into the research topics of 'An efficient modeling technique for RF MEMS phase shifter based on RBF neural network'. Together they form a unique fingerprint.

Cite this