Application of Neural Networks in the Development of Nonlinear Error Modeling and Test Point Prediction

Published

May 1, 2000

Author(s)

X. Han, Gerard N. Stenbakken, F. J. Von Zuben, Hans Engler

Abstract

This paper explores the neural network approach for empirical nonlinear error modeling. For systems that have a significant amount of nonlinearity, nonlinear error models require fewer parameters compared to linear models and require fewer test points to achieve the same prediction accuracy level. A neural network with a five-layer structure is investigated in this paper for this nonlinear empirical error modeling approach. The test point predictions of nonlinear modeling are compared with the results of linear modeling for an artificial nonlinear model, a circuit with nonlinearity, and an instrument with suspected nonlinearity. The nonlinear modeling shows more improvement when the data set contains more nonlinearity.

Proceedings Title

Proc. IEEE Instrumentation and Technology Conference (IMTC)

Volume

2

Conference Dates

May 1-4, 2000

Conference Location

Baltimore, MD

Pub Type

Conferences

Download Paper

Local Download

Keywords

modeling, neural networks, nonlinear circuits, nonlinear fitting, test point prediction

Citation

Han, X. , Stenbakken, G. , Von Zuben, F. and Engler, H. (2000), Application of Neural Networks in the Development of Nonlinear Error Modeling and Test Point Prediction, Proc. IEEE Instrumentation and Technology Conference (IMTC), Baltimore, MD, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=7751 (Accessed April 19, 2024)