Detecting abnormalities in aluminium reduction cells based on process events using multi-way principal component analysis (MPCA)

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

In the aluminium industry optimal production and quality products are major process targets. One way to achieve these targets is by improving the process control of aluminium reduction cells, and this is the aim of this research. This research proposes to apply an advanced multivariate control chart to aluminium reduction cells in a manner which provides new insights into process abnormalities and their diagnosis. The proposed approach uses multi-way principal component analysis to observe the movement of data towards abnormality after process events. Preliminary results showed that using the proposed approach could detect anode spikes after anode changing or tapping. Data with anode spikes present moved in a different direction than the data with anode spikes absent. An anode spike trajectory could be set up based on this discrimination. Data which move towards the anode spike trajectory have a high possibility of having anode spikes. Therefore based on this trajectory, the cell could be monitored ahead of time for spikes, and operations may take action to search for them much earlier. This will lead to a real-time fault detection system and is expected to assist process engineers in improving the process control of aluminium reduction cells.

Original languageEnglish
Title of host publicationTMS Annual Meeting
Pages589-593
Number of pages5
Publication statusPublished - 2009
Externally publishedYes
EventTMS 2009 Annual Meeting and Exhibition - San Francisco, CA
Duration: 16 Feb 200919 Feb 2009

Other

OtherTMS 2009 Annual Meeting and Exhibition
CitySan Francisco, CA
Period16/2/0919/2/09

Fingerprint

abnormalities
principal components analysis
Aluminum
spikes
Principal component analysis
Anodes
anodes
aluminum
cells
Trajectories
trajectories
Process control
fault detection
charts
Fault detection
engineers
discrimination
industries
Engineers
products

Keywords

  • Anode Spikes and Statistical Process Control
  • Principal Component Analysis
  • Process monitoring

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Mechanics of Materials
  • Metals and Alloys
  • Materials Chemistry

Cite this

Detecting abnormalities in aluminium reduction cells based on process events using multi-way principal component analysis (MPCA). / Abd Majid, Nazatul Aini; Young, Brent R.; Taylor, Mark P.; Chen, John J J.

TMS Annual Meeting. 2009. p. 589-593.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abd Majid, NA, Young, BR, Taylor, MP & Chen, JJJ 2009, Detecting abnormalities in aluminium reduction cells based on process events using multi-way principal component analysis (MPCA). in TMS Annual Meeting. pp. 589-593, TMS 2009 Annual Meeting and Exhibition, San Francisco, CA, 16/2/09.
@inproceedings{d658ac28a1c54b3ba4c0661050e3e117,
title = "Detecting abnormalities in aluminium reduction cells based on process events using multi-way principal component analysis (MPCA)",
abstract = "In the aluminium industry optimal production and quality products are major process targets. One way to achieve these targets is by improving the process control of aluminium reduction cells, and this is the aim of this research. This research proposes to apply an advanced multivariate control chart to aluminium reduction cells in a manner which provides new insights into process abnormalities and their diagnosis. The proposed approach uses multi-way principal component analysis to observe the movement of data towards abnormality after process events. Preliminary results showed that using the proposed approach could detect anode spikes after anode changing or tapping. Data with anode spikes present moved in a different direction than the data with anode spikes absent. An anode spike trajectory could be set up based on this discrimination. Data which move towards the anode spike trajectory have a high possibility of having anode spikes. Therefore based on this trajectory, the cell could be monitored ahead of time for spikes, and operations may take action to search for them much earlier. This will lead to a real-time fault detection system and is expected to assist process engineers in improving the process control of aluminium reduction cells.",
keywords = "Anode Spikes and Statistical Process Control, Principal Component Analysis, Process monitoring",
author = "{Abd Majid}, {Nazatul Aini} and Young, {Brent R.} and Taylor, {Mark P.} and Chen, {John J J}",
year = "2009",
language = "English",
isbn = "9780873397353",
pages = "589--593",
booktitle = "TMS Annual Meeting",

}

TY - GEN

T1 - Detecting abnormalities in aluminium reduction cells based on process events using multi-way principal component analysis (MPCA)

AU - Abd Majid, Nazatul Aini

AU - Young, Brent R.

AU - Taylor, Mark P.

AU - Chen, John J J

PY - 2009

Y1 - 2009

N2 - In the aluminium industry optimal production and quality products are major process targets. One way to achieve these targets is by improving the process control of aluminium reduction cells, and this is the aim of this research. This research proposes to apply an advanced multivariate control chart to aluminium reduction cells in a manner which provides new insights into process abnormalities and their diagnosis. The proposed approach uses multi-way principal component analysis to observe the movement of data towards abnormality after process events. Preliminary results showed that using the proposed approach could detect anode spikes after anode changing or tapping. Data with anode spikes present moved in a different direction than the data with anode spikes absent. An anode spike trajectory could be set up based on this discrimination. Data which move towards the anode spike trajectory have a high possibility of having anode spikes. Therefore based on this trajectory, the cell could be monitored ahead of time for spikes, and operations may take action to search for them much earlier. This will lead to a real-time fault detection system and is expected to assist process engineers in improving the process control of aluminium reduction cells.

AB - In the aluminium industry optimal production and quality products are major process targets. One way to achieve these targets is by improving the process control of aluminium reduction cells, and this is the aim of this research. This research proposes to apply an advanced multivariate control chart to aluminium reduction cells in a manner which provides new insights into process abnormalities and their diagnosis. The proposed approach uses multi-way principal component analysis to observe the movement of data towards abnormality after process events. Preliminary results showed that using the proposed approach could detect anode spikes after anode changing or tapping. Data with anode spikes present moved in a different direction than the data with anode spikes absent. An anode spike trajectory could be set up based on this discrimination. Data which move towards the anode spike trajectory have a high possibility of having anode spikes. Therefore based on this trajectory, the cell could be monitored ahead of time for spikes, and operations may take action to search for them much earlier. This will lead to a real-time fault detection system and is expected to assist process engineers in improving the process control of aluminium reduction cells.

KW - Anode Spikes and Statistical Process Control

KW - Principal Component Analysis

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=67449162244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67449162244&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780873397353

SP - 589

EP - 593

BT - TMS Annual Meeting

ER -