Share Email Print

Proceedings Paper

Modeling the sensor calibration based on RNN with feature extraction
Author(s): Hui Zhang; Yong Ni; Yue Chang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this work a novel method is proposed for the sensor calibration, by combining Recurrent Neural Network (RNN) with feature extraction. RNN is used as the neural network model trained to calibrate the measuring error, while Kernel Independent Component Analysis (KICA) and Independent Component Analysis (ICA) are introduced in as the feature extraction as comparison. And by examining the data of an example of temperature sensor calibration of Agilent 34970, it is shown that the proposed methods can both perform good calibration comparing with single RBF method. And the KICA method performs better than the ICA method.

Paper Details

Date Published: 31 December 2008
PDF: 6 pages
Proc. SPIE 7130, Fourth International Symposium on Precision Mechanical Measurements, 713019 (31 December 2008); doi: 10.1117/12.819583
Show Author Affiliations
Hui Zhang, Hefei Univ. of Technology (China)
Yong Ni, Hefei Univ. of Technology (China)
Yue Chang, Hefei Univ. of Technology (China)

Published in SPIE Proceedings Vol. 7130:
Fourth International Symposium on Precision Mechanical Measurements
Yetai Fei; Kuang-Chao Fan; Rongsheng Lu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?