Yield-driven electromagnetic optimization via space mapping-based neuromodels

被引:44
作者
Bandler, JW [1 ]
Rayas-Sánchez, JE
Zhang, QJ
机构
[1] McMaster Univ, Simulat Opt Syst Res Lab, Hamilton, ON L8S 4K1, Canada
[2] McMaster Univ, Dept Elect & Comp Engn, Hamilton, ON L8S 4K1, Canada
[3] Bandler Corp, Dundas, ON L9H 5E7, Canada
[4] Carleton Univ, Dept Elect, Ottawa, ON K1S 5B6, Canada
关键词
neural network applications; space mapping; optimization methods; design automation; EM optimization; neural space mapping; statistical analysis; yield optimization; design centering; microwave circuits; microstrip filters; neural modeling;
D O I
10.1002/mmce.10015
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Accurate yield optimization and statistical analysis of microwave components are crucial ingredients for manufacturability-driven designs in a time-to-market development environment. Yield optimization requires intensive simulations to cover the entire statistic of possible outcomes of a given manufacturing process. Performing direct yield Optimization using accurate full-wave electromagnetic simulations does not appear feasible. In this article, an efficient procedure to realize electromagnetics (EM) based yield optimization and statistical analysis of microwave structures using space mapping-based neuromodels is proposed. Our technique is illustrated by the EM-based statistical analysis and yield optimization of a high temperature superconducting (HTS) microstrip filter. (C) 2002 John Wiley & Sons, Inc.
引用
收藏
页码:79 / 89
页数:11
相关论文
共 26 条
[1]  
[Anonymous], NEURAL NETWORKS RF M
[2]   Neural space-mapping optimization for EM-based design [J].
Bakr, MH ;
Bandler, JW ;
Ismail, MA ;
Rayas-Sánchez, JE ;
Zhang, QJ .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2000, 48 (12) :2307-2315
[3]  
Bakr MH, 2000, IEEE MTT-S, P879, DOI 10.1109/MWSYM.2000.863320
[4]   A hybrid aggressive space-mapping algorithm for EM optimization [J].
Bakr, MH ;
Bandler, JW ;
Georgieva, N ;
Madsen, K .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1999, 47 (12) :2440-2449
[5]   YIELD-DRIVEN ELECTROMAGNETIC OPTIMIZATION VIA MULTILEVEL MULTIDIMENSIONAL MODELS [J].
BANDLER, JW ;
BIERNACKI, RM ;
CHEN, SH ;
GROBELNY, PA ;
YE, S .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1993, 41 (12) :2269-2278
[6]   Neuromodeling of microwave circuits exploiting space-mapping technology [J].
Bandler, JW ;
Ismail, MA ;
Rayas-Sánchez, JE ;
Zhang, QJ .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1999, 47 (12) :2417-2427
[7]   CIRCUIT OPTIMIZATION - THE STATE OF THE ART [J].
BANDLER, JW ;
CHEN, SH .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1988, 36 (02) :424-443
[8]  
BANDLER JW, 1994, P IEEE INT S CIRC SY, V1, P145
[9]  
Burrascano P, 1998, IEEE MTT S INT MICR, P13, DOI 10.1109/MWSYM.1998.689313
[10]  
Burrascano P, 1999, INT J RF MICROW C E, V9, P158, DOI 10.1002/(SICI)1099-047X(199905)9:3<158::AID-MMCE3>3.0.CO