The analysis and design of microwave filters obtained by the insertion of cylindrical posts in a rectangular waveguide is in this paper implemented by a neural network approach. The neural architecture is able to give an accurate description of the filtering device behaviour in almost real time, whereas the full wave simulator would take several minutes. This kind of approach is suitable to analyse a cascade of multiple posts and to provide a solution for the synthesis of such a filtering device.
Fem-trained Artificial Neural Networks For The Analysis And Design Of Cylindrical Posts In A Rectangular Waveguide / G. Fedi; S. Manetti; G. Pelosi; S. Selleri. - In: ELECTROMAGNETICS. - ISSN 0272-6343. - STAMPA. - 22:(2002), pp. 323-330. [10.1080/02726340290083923]
Fem-trained Artificial Neural Networks For The Analysis And Design Of Cylindrical Posts In A Rectangular Waveguide
MANETTI, STEFANO;PELOSI, GIUSEPPE;SELLERI, STEFANO
2002
Abstract
The analysis and design of microwave filters obtained by the insertion of cylindrical posts in a rectangular waveguide is in this paper implemented by a neural network approach. The neural architecture is able to give an accurate description of the filtering device behaviour in almost real time, whereas the full wave simulator would take several minutes. This kind of approach is suitable to analyse a cascade of multiple posts and to provide a solution for the synthesis of such a filtering device.
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
