Diagnosing faults in aluminium processing by using multivariate statistical approaches

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

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Multivariate statistical approaches are expected to detect and diagnose faults effectively for complex materials processing including steel, iron, copper and aluminium processing. This advanced monitoring of materials processing is essential to address abnormal or faulty conditions in a timely manner. In the aluminium-smelting process, late diagnosis of abnormal conditions such as an anode effect can result in an increase of energy consumption and emission of greenhouse gases. In this article, a new statistical framework is proposed that is based on hierarchal diagnostic approach to diagnose two groups of faults, anode faults and non-anode faults. The system diagnoses faults by predicting the type of fault based on continuous, non-linear and multivariate process data using discriminant partial least squares (DPLS). The new system goes beyond the typical multivariate system in that it also includes the dynamic behaviour of the process during anode changing and alumina feeding. The results of performance evaluation of the new diagnosis system tested using real-data show that the system can diagnose the two groups of faults.

Original languageEnglish
Pages (from-to)1268-1279
Number of pages12
JournalJournal of Materials Science
Volume47
Issue number3
DOIs
Publication statusPublished - Feb 2012

Fingerprint

Aluminum
Anodes
Processing
Failure analysis
Aluminum Oxide
Steel
Smelting
Greenhouse gases
Copper
Alumina
Energy utilization
Iron
Monitoring

ASJC Scopus subject areas

  • Materials Science(all)
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Diagnosing faults in aluminium processing by using multivariate statistical approaches. / Abd Majid, Nazatul Aini; Taylor, Mark P.; Chen, John J J J; Yu, Wei; Young, Brent R.

In: Journal of Materials Science, Vol. 47, No. 3, 02.2012, p. 1268-1279.

Research output: Contribution to journalArticle

Abd Majid, Nazatul Aini ; Taylor, Mark P. ; Chen, John J J J ; Yu, Wei ; Young, Brent R. / Diagnosing faults in aluminium processing by using multivariate statistical approaches. In: Journal of Materials Science. 2012 ; Vol. 47, No. 3. pp. 1268-1279.
@article{14f75dbb9afe43d18cdd811d57c83de2,
title = "Diagnosing faults in aluminium processing by using multivariate statistical approaches",
abstract = "Multivariate statistical approaches are expected to detect and diagnose faults effectively for complex materials processing including steel, iron, copper and aluminium processing. This advanced monitoring of materials processing is essential to address abnormal or faulty conditions in a timely manner. In the aluminium-smelting process, late diagnosis of abnormal conditions such as an anode effect can result in an increase of energy consumption and emission of greenhouse gases. In this article, a new statistical framework is proposed that is based on hierarchal diagnostic approach to diagnose two groups of faults, anode faults and non-anode faults. The system diagnoses faults by predicting the type of fault based on continuous, non-linear and multivariate process data using discriminant partial least squares (DPLS). The new system goes beyond the typical multivariate system in that it also includes the dynamic behaviour of the process during anode changing and alumina feeding. The results of performance evaluation of the new diagnosis system tested using real-data show that the system can diagnose the two groups of faults.",
author = "{Abd Majid}, {Nazatul Aini} and Taylor, {Mark P.} and Chen, {John J J J} and Wei Yu and Young, {Brent R.}",
year = "2012",
month = "2",
doi = "10.1007/s10853-011-5884-y",
language = "English",
volume = "47",
pages = "1268--1279",
journal = "Journal of Materials Science",
issn = "0022-2461",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Diagnosing faults in aluminium processing by using multivariate statistical approaches

AU - Abd Majid, Nazatul Aini

AU - Taylor, Mark P.

AU - Chen, John J J J

AU - Yu, Wei

AU - Young, Brent R.

PY - 2012/2

Y1 - 2012/2

N2 - Multivariate statistical approaches are expected to detect and diagnose faults effectively for complex materials processing including steel, iron, copper and aluminium processing. This advanced monitoring of materials processing is essential to address abnormal or faulty conditions in a timely manner. In the aluminium-smelting process, late diagnosis of abnormal conditions such as an anode effect can result in an increase of energy consumption and emission of greenhouse gases. In this article, a new statistical framework is proposed that is based on hierarchal diagnostic approach to diagnose two groups of faults, anode faults and non-anode faults. The system diagnoses faults by predicting the type of fault based on continuous, non-linear and multivariate process data using discriminant partial least squares (DPLS). The new system goes beyond the typical multivariate system in that it also includes the dynamic behaviour of the process during anode changing and alumina feeding. The results of performance evaluation of the new diagnosis system tested using real-data show that the system can diagnose the two groups of faults.

AB - Multivariate statistical approaches are expected to detect and diagnose faults effectively for complex materials processing including steel, iron, copper and aluminium processing. This advanced monitoring of materials processing is essential to address abnormal or faulty conditions in a timely manner. In the aluminium-smelting process, late diagnosis of abnormal conditions such as an anode effect can result in an increase of energy consumption and emission of greenhouse gases. In this article, a new statistical framework is proposed that is based on hierarchal diagnostic approach to diagnose two groups of faults, anode faults and non-anode faults. The system diagnoses faults by predicting the type of fault based on continuous, non-linear and multivariate process data using discriminant partial least squares (DPLS). The new system goes beyond the typical multivariate system in that it also includes the dynamic behaviour of the process during anode changing and alumina feeding. The results of performance evaluation of the new diagnosis system tested using real-data show that the system can diagnose the two groups of faults.

UR - http://www.scopus.com/inward/record.url?scp=84855497035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855497035&partnerID=8YFLogxK

U2 - 10.1007/s10853-011-5884-y

DO - 10.1007/s10853-011-5884-y

M3 - Article

VL - 47

SP - 1268

EP - 1279

JO - Journal of Materials Science

JF - Journal of Materials Science

SN - 0022-2461

IS - 3

ER -