Detecting variations of small-signal equivalent-circuit model parameters in the Si/SiGe HBT process with ANN

被引:5
|
作者
Taher, H
Schreurs, D
Gillon, R
Vestiel, E
van Niekerk, C
Alabadelah, A
Nauwelaers, B
机构
[1] Katholieke Univ Leuven, TELEMIC, Div ESAT, B-3001 Heverlee, Belgium
[2] AMI Semicond, Technol R&D Dept, B-9700 Oudenaarde, Belgium
[3] Univ Stellenbosch, Dept Elect & Elect Engn, ZA-7602 Stellenbosch, South Africa
关键词
de-embedding; small-signal modeling; artificial neural network; SiGeHBT;
D O I
10.1002/mmce.20056
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
To capture variations in the Si/SiGe HBT process characteristics, we could extract a complete equivalent-circuit model for each device, but this would be a time-consuming process. In this article, we develop an alternative approach based on an artificial neural network (ANN). To keep the complexity of the ANN low, we limit this mapping to the most sensitive elements by utilizing sensitivity analysis on a reference device. The results show that the ANN predicts the model parameters very well. (C) 2004 Wiley Periodicals, Inc.
引用
收藏
页码:102 / 108
页数:7
相关论文
共 50 条