Design of cylindrical posts in rectangular waveguide by neural network approach

Author

Fedi, G. ; Manetti, S. ; Pelosi, G. ; Selleri, S.

Author_Institution

Dept. of Electron. & Telecommun., Florence Univ., Italy

Volume

2

fYear

2000

fDate

16-21 July 2000

Firstpage

1054

Abstract

Full wave analysis of cylindrical posts in rectangular waveguide for antenna networks is in this paper replaced with a properly trained artificial neural network. The network is able to give an accurate description of the post behaviour at a given frequency in real time, whereas the full wave simulator would take several minutes. This will be of great importance in synthesis problem.

Keywords

antenna feeds; digital simulation; electrical engineering computing; learning (artificial intelligence); microwave filters; multilayer perceptrons; rectangular waveguides; waveguide filters; antenna feeding network; antenna receiving network; cylindrical posts; frequency; full wave analysis; full wave simulator; microwave waveguide filter; multilayer perceptron; post behaviour; rectangular waveguide; synthesis problem; trained artificial neural network; Artificial neural networks; Circuit simulation; Circuit synthesis; Frequency estimation; Geometry; Intelligent networks; Microwave filters; Network synthesis; Neural networks; Rectangular waveguides;

fLanguage

English

Publisher

ieee

Conference_Titel

Antennas and Propagation Society International Symposium, 2000. IEEE

Conference_Location

Salt Lake City, UT, USA

Print_ISBN

0-7803-6369-8

Type

conf

DOI

10.1109/APS.2000.875403

Filename

875403