Aluminium process fault detection by Multiway Principal Component Analysis

Nazatul Aini Abd Majid, Mark P. Taylor, John J J Chen, Marco A. Stam, Albert Mulder, Brent R. Young

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Real-time fault detection is difficult to perform in an aluminium smelter because the continuous aluminium electrolysis is operated batchwise in terms of material additions, meaning the measurements obtained from the process are dynamic, multivariate and limited. This paper presents a new framework based on Multiway Principal Component Analysis (MPCA) to detect faults in real-time in the industrial continuous aluminium electrolysis process. This real-time fault detection system incorporates the dynamic behaviour of two important operations in the continuous aluminium electrolysis process, alumina feeding and anode changing. The methodology is demonstrated using real data from an operating aluminium smelter, and is shown to be effective in the early detection of anode spikes and anode effects.

Original languageEnglish
Pages (from-to)367-379
Number of pages13
JournalControl Engineering Practice
Volume19
Issue number4
DOIs
Publication statusPublished - Apr 2011
Externally publishedYes

Fingerprint

Multiway Analysis
Fault Detection
Fault detection
Principal component analysis
Aluminum
Principal Component Analysis
Electrolysis
Anodes
Real-time
Alumina
Spike
Dynamic Behavior
Fault
Methodology

Keywords

  • Aluminium electrolysis
  • Anode effects
  • Anode spikes
  • Multiway PCA
  • Real-time fault detection

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Computer Science Applications

Cite this

Aluminium process fault detection by Multiway Principal Component Analysis. / Abd Majid, Nazatul Aini; Taylor, Mark P.; Chen, John J J; Stam, Marco A.; Mulder, Albert; Young, Brent R.

In: Control Engineering Practice, Vol. 19, No. 4, 04.2011, p. 367-379.

Research output: Contribution to journalArticle

Abd Majid, Nazatul Aini ; Taylor, Mark P. ; Chen, John J J ; Stam, Marco A. ; Mulder, Albert ; Young, Brent R. / Aluminium process fault detection by Multiway Principal Component Analysis. In: Control Engineering Practice. 2011 ; Vol. 19, No. 4. pp. 367-379.
@article{d4c05f3eb7594d0d95a09451143572cb,
title = "Aluminium process fault detection by Multiway Principal Component Analysis",
abstract = "Real-time fault detection is difficult to perform in an aluminium smelter because the continuous aluminium electrolysis is operated batchwise in terms of material additions, meaning the measurements obtained from the process are dynamic, multivariate and limited. This paper presents a new framework based on Multiway Principal Component Analysis (MPCA) to detect faults in real-time in the industrial continuous aluminium electrolysis process. This real-time fault detection system incorporates the dynamic behaviour of two important operations in the continuous aluminium electrolysis process, alumina feeding and anode changing. The methodology is demonstrated using real data from an operating aluminium smelter, and is shown to be effective in the early detection of anode spikes and anode effects.",
keywords = "Aluminium electrolysis, Anode effects, Anode spikes, Multiway PCA, Real-time fault detection",
author = "{Abd Majid}, {Nazatul Aini} and Taylor, {Mark P.} and Chen, {John J J} and Stam, {Marco A.} and Albert Mulder and Young, {Brent R.}",
year = "2011",
month = "4",
doi = "10.1016/j.conengprac.2010.12.005",
language = "English",
volume = "19",
pages = "367--379",
journal = "Control Engineering Practice",
issn = "0967-0661",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Aluminium process fault detection by Multiway Principal Component Analysis

AU - Abd Majid, Nazatul Aini

AU - Taylor, Mark P.

AU - Chen, John J J

AU - Stam, Marco A.

AU - Mulder, Albert

AU - Young, Brent R.

PY - 2011/4

Y1 - 2011/4

N2 - Real-time fault detection is difficult to perform in an aluminium smelter because the continuous aluminium electrolysis is operated batchwise in terms of material additions, meaning the measurements obtained from the process are dynamic, multivariate and limited. This paper presents a new framework based on Multiway Principal Component Analysis (MPCA) to detect faults in real-time in the industrial continuous aluminium electrolysis process. This real-time fault detection system incorporates the dynamic behaviour of two important operations in the continuous aluminium electrolysis process, alumina feeding and anode changing. The methodology is demonstrated using real data from an operating aluminium smelter, and is shown to be effective in the early detection of anode spikes and anode effects.

AB - Real-time fault detection is difficult to perform in an aluminium smelter because the continuous aluminium electrolysis is operated batchwise in terms of material additions, meaning the measurements obtained from the process are dynamic, multivariate and limited. This paper presents a new framework based on Multiway Principal Component Analysis (MPCA) to detect faults in real-time in the industrial continuous aluminium electrolysis process. This real-time fault detection system incorporates the dynamic behaviour of two important operations in the continuous aluminium electrolysis process, alumina feeding and anode changing. The methodology is demonstrated using real data from an operating aluminium smelter, and is shown to be effective in the early detection of anode spikes and anode effects.

KW - Aluminium electrolysis

KW - Anode effects

KW - Anode spikes

KW - Multiway PCA

KW - Real-time fault detection

UR - http://www.scopus.com/inward/record.url?scp=79953041929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953041929&partnerID=8YFLogxK

U2 - 10.1016/j.conengprac.2010.12.005

DO - 10.1016/j.conengprac.2010.12.005

M3 - Article

VL - 19

SP - 367

EP - 379

JO - Control Engineering Practice

JF - Control Engineering Practice

SN - 0967-0661

IS - 4

ER -