A soft sensor for the Bayer process

Vincent Cregan, William Lee, Louise Clune

Research output: Contribution to journalArticle

Abstract

A soft sensor for measuring product quality in the Bayer process has been developed. The soft sensor uses a combination of historical process data recorded from online sensors and laboratory measurements to predict a key quality indicator, namely particle strength. Stepwise linear regression is used to select the relevant variables from a large dataset composed of monitored properties and laboratory data. The developed sensor is employed successfully by RUSAL Aughinish Alumina Ltd to predict product strength five days into the future with R-squared equal to 0.75 and to capture deviations from standard operating conditions.
LanguageEnglish
Number of pages6
JournalJournal of Mathematics in Industry
Volume7
Issue number7
DOIs
Publication statusPublished - 4 May 2017
Externally publishedYes

Fingerprint

Soft Sensor
Bayes
Predict
Sensor
Alumina
Sensors
Linear regression
Large Data Sets
Deviation
Standards

Cite this

Cregan, Vincent ; Lee, William ; Clune, Louise. / A soft sensor for the Bayer process. In: Journal of Mathematics in Industry. 2017 ; Vol. 7, No. 7.
@article{74b44e3aa8444d689af6c991ea9f49df,
title = "A soft sensor for the Bayer process",
abstract = "A soft sensor for measuring product quality in the Bayer process has been developed. The soft sensor uses a combination of historical process data recorded from online sensors and laboratory measurements to predict a key quality indicator, namely particle strength. Stepwise linear regression is used to select the relevant variables from a large dataset composed of monitored properties and laboratory data. The developed sensor is employed successfully by RUSAL Aughinish Alumina Ltd to predict product strength five days into the future with R-squared equal to 0.75 and to capture deviations from standard operating conditions.",
keywords = "Bayer process, soft sensor, stepwise multiple linear regression",
author = "Vincent Cregan and William Lee and Louise Clune",
year = "2017",
month = "5",
day = "4",
doi = "10.1186/s13362-017-0037-9",
language = "English",
volume = "7",
journal = "Journal of Mathematics in Industry",
issn = "2190-5983",
publisher = "Springer Verlag",
number = "7",

}

A soft sensor for the Bayer process. / Cregan, Vincent; Lee, William; Clune, Louise.

In: Journal of Mathematics in Industry, Vol. 7, No. 7, 04.05.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A soft sensor for the Bayer process

AU - Cregan, Vincent

AU - Lee, William

AU - Clune, Louise

PY - 2017/5/4

Y1 - 2017/5/4

N2 - A soft sensor for measuring product quality in the Bayer process has been developed. The soft sensor uses a combination of historical process data recorded from online sensors and laboratory measurements to predict a key quality indicator, namely particle strength. Stepwise linear regression is used to select the relevant variables from a large dataset composed of monitored properties and laboratory data. The developed sensor is employed successfully by RUSAL Aughinish Alumina Ltd to predict product strength five days into the future with R-squared equal to 0.75 and to capture deviations from standard operating conditions.

AB - A soft sensor for measuring product quality in the Bayer process has been developed. The soft sensor uses a combination of historical process data recorded from online sensors and laboratory measurements to predict a key quality indicator, namely particle strength. Stepwise linear regression is used to select the relevant variables from a large dataset composed of monitored properties and laboratory data. The developed sensor is employed successfully by RUSAL Aughinish Alumina Ltd to predict product strength five days into the future with R-squared equal to 0.75 and to capture deviations from standard operating conditions.

KW - Bayer process

KW - soft sensor

KW - stepwise multiple linear regression

U2 - 10.1186/s13362-017-0037-9

DO - 10.1186/s13362-017-0037-9

M3 - Article

VL - 7

JO - Journal of Mathematics in Industry

T2 - Journal of Mathematics in Industry

JF - Journal of Mathematics in Industry

SN - 2190-5983

IS - 7

ER -