DocumentCode :
2733524
Title :
A combined transfer function and neural network method for modeling via in multilayer circuits
Author :
Xin Zhang ; Cao, Yazi ; Zhang, Q.J.
Author_Institution :
Dept. of Electron., Carleton Univ., Ottawa, ON
fYear :
2008
fDate :
10-13 Aug. 2008
Firstpage :
73
Lastpage :
76
Abstract :
A new approach for via modeling in multilayer circuits is presented in this paper. The proposed technique combines transfer function with neural network to enhance the learning ability of neural network. It is capable of providing accurate simulation models even if an equivalent circuit is not available. It retains the EM level accuracy and reduces CPU time significantly compared to EM simulator. Examples of via holes for both multilayer printed circuit boards and integrated circuits are presented to demonstrate the accuracy and efficiency of this proposed method.
Keywords :
circuit simulation; equivalent circuits; neural nets; printed circuits; transfer function matrices; equivalent circuit; integrated circuits; multilayer circuits; multilayer printed circuit boards; neural network method; simulation models; transfer function method; Artificial neural networks; Circuit simulation; Equivalent circuits; Frequency; Integrated circuit interconnections; Multi-layer neural network; Neural networks; Neurons; Solid modeling; Transfer functions;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2008. MWSCAS 2008. 51st Midwest Symposium on
Conference_Location :
Knoxville, TN
ISSN :
1548-3746
Print_ISBN :
978-1-4244-2166-4
Electronic_ISBN :
1548-3746
Type :
conf
DOI :
10.1109/MWSCAS.2008.4616739
Filename :
4616739
Link To Document :
بازگشت