Application of online support vector regression for soft sensors

Hiromasa Kaneko; Kimito Funatsu

doi:10.1002/aic.14299

journal article Dec 19, 2013

Application of online support vector regression for soft sensors

Hiromasa Kaneko

Kimito Funatsu

AIChE Journal Vol. 60 No. 2 pp. 600-612 · Wiley

View at Publisher Save 10.1002/aic.14299

Abstract

Soft sensors have been widely used in chemical plants to estimate process variables that are difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes in state of chemical plants. Characteristics of adaptive soft sensor models such as moving window models, just‐in‐time models and time difference models were previously discussed. The predictive accuracy of any traditional models decreases when sudden changes in processes occur. Therefore, a new soft sensor method based on online support vector regression (SVR) and the time variable was developed for constructing soft sensor models adaptive to rapid changes of relationships among process variables. A nonlinear SVR model with the time variable is updated with the most recent data. The proposed method was applied to simulation data and real industrial data, and achieved higher predictive accuracy than traditional ones even when time‐varying changes in process characteristics happen. © 2013 American Institute of Chemical Engineers AIChE J 60: 600–612, 2014

Topics

No keywords indexed for this article. Browse by subject →

References

31

[1]

10.1016/j.compchemeng.2008.12.012

[2]

10.1002/aic.11648

[3]

10.1002/aic.12346

[4]

10.1016/s0098-1354(97)00262-7

[5]

10.1016/j.ces.2004.04.020

[6]

10.1002/aic.11791

[7]

10.1023/a:1015727715131

[8]

Maintenance-free soft sensor models with time difference of process variables

Hiromasa Kaneko, Kimito Funatsu

Chemometrics and Intelligent Laboratory Systems 10.1016/j.chemolab.2011.04.016

[9]

10.1016/j.chemolab.2011.09.003

[10]

10.1021/ie200692m

[11]

10.1016/j.compchemeng.2010.07.034

[12]

10.1021/ie3020186

[13]

10.1016/j.compchemeng.2012.03.004

[14]

Okada T "Development of a model selection method based on reliability of a soft sensor model" Songklanakarin J Sci Technol. (2012)

[15]

10.1002/aic.14006

[16]

10.1162/089976603322385117

[17]

10.1007/978-0-387-45528-0

[18]

10.1016/j.compchemeng.2013.07.016

[19]

10.1002/acs.919

[20]

Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions

Manoel Castro-Neto, Young-Seon Jeong, Myong-Kee Jeong et al.

Expert Systems with Applications 10.1016/j.eswa.2008.07.069

[21]

10.1007/s11548-009-0355-5

[22]

10.1109/tsmca.2010.2055156

[23]

ParrellaF.Online Support Vector Regression. Software available athttp://onlinesvr.altervista.org/(accessed December 14 2013).

[24]

PLS-regression: a basic tool of chemometrics

Svante Wold, Michael Sjöström, Lennart Eriksson

Chemometrics and Intelligent Laboratory Systems 10.1016/s0169-7439(01)00155-1

[25]

10.1016/j.ijpharm.2011.10.007

[26]

10.1007/s00158-009-0395-z

[27]

10.1002/aic.690370605

[28]

10.1016/s0959-1524(99)00042-6

[29]

10.1252/jcej.07we032

[30]

10.1021/ie049500h

[31]

10.1016/j.compchemeng.2010.09.003

Cited By

94

A quality-relevant deep rule-based system with complementary lifelong learning for adaptive quality prediction in industrial semi-supervised process data streams

Yu Gao, Huaiping Jin · 2025

Information Sciences

Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE

Xiaofeng Yuan, Biao Huang · 2018

IEEE Transactions on Industrial Inf...

Metrics

94

Citations

31

References

Details

Published: Dec 19, 2013
Vol/Issue: 60(2)
Pages: 600-612
License: View

Authors

H

Hiromasa Kaneko

Dept. of Chemical System Engineering The University of Tokyo Hongo 7‐3‐1, Bunkyo‐ku Tokyo 113–8656 Japan

K

Kimito Funatsu

Dept. of Chemical System Engineering The University of Tokyo Hongo 7‐3‐1, Bunkyo‐ku Tokyo 113–8656 Japan

Funding

Japan Society for the Promotion of Science (JSPS) Award: 24760629

Mizuho Foundation for the Promotion of Sciences

Cite This Article

Hiromasa Kaneko, Kimito Funatsu (2013). Application of online support vector regression for soft sensors. AIChE Journal, 60(2), 600-612. https://doi.org/10.1002/aic.14299

Application of online support vector regression for soft sensors

You May Also Like