DocumentCode
2162730
Title
Artificial Neural Network Modeling for Improved On-Wafer Line-Reflect-Match Calibrations
Author
Jargon, Jeffrey A. ; Gupta, K.C.
Author_Institution
National Institute of Standards and Technology, RF Electronics Group, 325 Broadway, Boulder, CO 80303 USA. Tel 303.497.3596 | Fax 303.497.3970 | E-mail: jargon@boulder.nist.gov
fYear
2001
fDate
24-26 Sept. 2001
Firstpage
1
Lastpage
4
Abstract
We model a load using an artificial neural network (ANN) to improve an on-wafer line-reflect-match (LRM) calibration of a vector network analyzer (VNA). The ANN is trained with measurement data obtained from a thru-reflect-line (TRL) calibration. The accuracy of the LRM calibration using the ANN-modeled load compares favorably to a benchmark multiline TRL calibration with an average worst-case scattering parameter error bound of 0.017 over a 40-GHz bandwidth.
Keywords
Artificial neural networks; Calibration; Impedance measurement; Load modeling; Measurement standards; Neurons; Noise measurement; Probes; Reflection; Scattering parameters;
fLanguage
English
Publisher
ieee
Conference_Titel
Microwave Conference, 2001. 31st European
Conference_Location
London, England
Type
conf
DOI
10.1109/EUMA.2001.339007
Filename
4140075
Link To Document