Abstract
We model a coaxial load using an artificial neural network (ANN) to improve a coaxial line-reflect-match (LRM) calibration of an automatic network analyzer. 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 0.024 over an 18-GHz bandwidth. © 2001 John Wiley & Sons, Inc. Int J RF and Microwave CAE 11: 33–37, 2001.

This publication has 5 references indexed in Scilit: