Artificial Neural Network Modeling for Improved On-Wafer OSLT Calibration Standards

Published

September 1, 2000

Author(s)

Jeffrey Jargon, Kuldip Gupta, Donald C. DeGroot

Abstract

We apply artificial neural networks (ANNs) to improve the modeling of on-wafer open-short-load-thru (OSLT) standards used for calibrating vector network analyzers. The ANNs are trained with measurement data obtained from a benchmark multiline thru-reflect-line (TRL) calibration. We assess the accuracy of an OSLT calibration using these ANN-modeled standards, and find that it compares favorably (less than a 0.02 difference in magnitude) to the bench mark multiline TRL calibration over a 40 GHz bandwidth. We also quantify the training errors and training times as a function of bother the number of training points and the number of neurons in the hidden layer.

Citation

International Journal of Rf and Microwave Computer-Aided Engineering

Volume

10

Issue

5

Pub Type

Journals

Keywords

artificial neural network, calibration model, network analyzer, standards

Citation

Jargon, J. , Gupta, K. and DeGroot, D. (2000), Artificial Neural Network Modeling for Improved On-Wafer OSLT Calibration Standards, International Journal of Rf and Microwave Computer-Aided Engineering (Accessed October 10, 2025)