Title :
Yield-Driven EM Optimization using Space Mapping-Based Neuromodels
Author :
Bandler, J.W. ; Rayas-Sánchez, J.E. ; Zhang, Q.J.
Author_Institution :
Bandler Corporation, P.O. Box 8083, Dundas, Canada L9H 5E7; McMaster University, 1280 Main St. West, Hamilton, Canada L8S 4K1, j.bandler@ieee.org, bandler@mcmaster.ca
Abstract :
In this work, an efficient procedure to realize electromagnetics-based yield optimization and statistical analysis of microwave structures using space mapping-based neuromodels is proposed. A generalized relationship between the fine and coarse model sensitivities through the Jacobian of the neuromapping is proposed. Our technique is illustrated by the EM-based statistical analysis and yield optimization of an HTS microstrip filter.
Keywords :
Analytical models; Circuit simulation; Computational modeling; Frequency; High temperature superconductors; Jacobian matrices; Microstrip filters; Microwave filters; Neural networks; Statistical analysis;
Conference_Titel :
Microwave Conference, 2001. 31st European
Conference_Location :
London, England
DOI :
10.1109/EUMA.2001.338979