DocumentCode :
432631
Title :
A neural network method for the multilayered shielded green´s function calculation
Author :
Garcia, J.P. ; Rebenaque, D.C. ; Pereira, F.Q. ; Tornero, J.L.G. ; Melcon, Alejandro
Volume :
2
fYear :
2004
fDate :
12-14 Oct. 2004
Firstpage :
841
Lastpage :
844
Abstract :
Multilayered boxed Green??s Functions are needed in Integral Equation (IE) approaches, which combined with the method of moments (MOM) algorithm allows for the efficient analysis of printed shielded circuits. This analysis is computational time consuming, specially due to the slow convergence of the relevant boxed Green??s functions. Neural Networks as Radial Basis Function Networks can effectively approximate the multilayered media boxed Green??s functions, allowing a faster performance in the analysis of practical shielded MMIC devices.
Keywords :
Algorithm design and analysis; Circuits; Green´s function methods; Integral equations; MMICs; Message-oriented middleware; Moment methods; Multi-layer neural network; Neural networks; Radial basis function networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Microwave Conference, 2004. 34th European
Conference_Location :
Amsterdam, The Netherlands
Print_ISBN :
1-58053-992-0
Type :
conf
Filename :
1418954
Link To Document :
بازگشت