Multivariate statistical monitoring of the aluminium smelting process

Nazatul Aini Abd Majid, Mark P. Taylor, John J J Chen, Brent R. Young

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

This paper describes the development of a new 'cascade' monitoring system for the aluminium smelting process that uses latent variable models. This system is based on the changes of variability patterns within a feeding cycle which are used to provide indications of faults and their possible causes. The system has been tested offline using 31 data sets. The performance of the system to detect an anode effect has been compared with a typical latent variable model that monitors the change of behaviour at every time instant. The results show that the 'cascade' monitoring system is able to detect abnormal events. It was possible to relate each event with specific patterns associated with abnormalities thus facilitating later fault diagnosis.

Original languageEnglish
Pages (from-to)2457-2468
Number of pages12
JournalComputers and Chemical Engineering
Volume35
Issue number11
DOIs
Publication statusPublished - 15 Nov 2011
Externally publishedYes

Fingerprint

Smelting
Aluminum
Monitoring
Failure analysis
Anodes

Keywords

  • Aluminium electrolysis
  • Multiway principal component analysis (MPCA)
  • Process monitoring

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Computer Science Applications

Cite this

Multivariate statistical monitoring of the aluminium smelting process. / Abd Majid, Nazatul Aini; Taylor, Mark P.; Chen, John J J; Young, Brent R.

In: Computers and Chemical Engineering, Vol. 35, No. 11, 15.11.2011, p. 2457-2468.

Research output: Contribution to journalArticle

Abd Majid, Nazatul Aini ; Taylor, Mark P. ; Chen, John J J ; Young, Brent R. / Multivariate statistical monitoring of the aluminium smelting process. In: Computers and Chemical Engineering. 2011 ; Vol. 35, No. 11. pp. 2457-2468.
@article{f46b050e7ae646c2b1151c7237f595b9,
title = "Multivariate statistical monitoring of the aluminium smelting process",
abstract = "This paper describes the development of a new 'cascade' monitoring system for the aluminium smelting process that uses latent variable models. This system is based on the changes of variability patterns within a feeding cycle which are used to provide indications of faults and their possible causes. The system has been tested offline using 31 data sets. The performance of the system to detect an anode effect has been compared with a typical latent variable model that monitors the change of behaviour at every time instant. The results show that the 'cascade' monitoring system is able to detect abnormal events. It was possible to relate each event with specific patterns associated with abnormalities thus facilitating later fault diagnosis.",
keywords = "Aluminium electrolysis, Multiway principal component analysis (MPCA), Process monitoring",
author = "{Abd Majid}, {Nazatul Aini} and Taylor, {Mark P.} and Chen, {John J J} and Young, {Brent R.}",
year = "2011",
month = "11",
day = "15",
doi = "10.1016/j.compchemeng.2011.03.001",
language = "English",
volume = "35",
pages = "2457--2468",
journal = "Computers and Chemical Engineering",
issn = "0098-1354",
publisher = "Elsevier BV",
number = "11",

}

TY - JOUR

T1 - Multivariate statistical monitoring of the aluminium smelting process

AU - Abd Majid, Nazatul Aini

AU - Taylor, Mark P.

AU - Chen, John J J

AU - Young, Brent R.

PY - 2011/11/15

Y1 - 2011/11/15

N2 - This paper describes the development of a new 'cascade' monitoring system for the aluminium smelting process that uses latent variable models. This system is based on the changes of variability patterns within a feeding cycle which are used to provide indications of faults and their possible causes. The system has been tested offline using 31 data sets. The performance of the system to detect an anode effect has been compared with a typical latent variable model that monitors the change of behaviour at every time instant. The results show that the 'cascade' monitoring system is able to detect abnormal events. It was possible to relate each event with specific patterns associated with abnormalities thus facilitating later fault diagnosis.

AB - This paper describes the development of a new 'cascade' monitoring system for the aluminium smelting process that uses latent variable models. This system is based on the changes of variability patterns within a feeding cycle which are used to provide indications of faults and their possible causes. The system has been tested offline using 31 data sets. The performance of the system to detect an anode effect has been compared with a typical latent variable model that monitors the change of behaviour at every time instant. The results show that the 'cascade' monitoring system is able to detect abnormal events. It was possible to relate each event with specific patterns associated with abnormalities thus facilitating later fault diagnosis.

KW - Aluminium electrolysis

KW - Multiway principal component analysis (MPCA)

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=80052622597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052622597&partnerID=8YFLogxK

U2 - 10.1016/j.compchemeng.2011.03.001

DO - 10.1016/j.compchemeng.2011.03.001

M3 - Article

VL - 35

SP - 2457

EP - 2468

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

SN - 0098-1354

IS - 11

ER -