Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart

Kirill Filianin, Satu Pia Reinikainen, Tuomo Sainio, Heli Helaakoski, Vesa Kyllonen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Once a multivariate model is developed, it can be combined with tools and techniques from univariate statistical process control to form multivariate statistical process control tools. It allows development of advanced process monitoring strategies. In the current study, copper plant history data with multiple variables was successfully treated by principal component analysis to detect abnormal process behavior, particularly, in copper solvent extraction. The multivariate model was based on the concentration levels of main process metals recorded by the industrial on-stream x-ray fluorescence analyzer. Normal operating conditions were defined through control limits that were assigned to Hotelling T2 values on x-axis and to squared prediction error values on y-axis. Samples that were beyond the limits were classified as either systematic or random errors, or outliers. Model testing showed successful application of control limits to detect abnormal behavior of copper solvent extraction process as early warnings. Compared to the conventional univariate techniques of analyzing one variable at a time, the proposed model allows to detect on-line a process failure summarizing information from all process variables simultaneously. The proposed methodology was combined with on-line quality monitoring tool developed by VTT, Technical Research Center of Finland, to visualize the results. Thus, the proposed approach has a potential in on-line industrial instrumentation providing fast, robust and cheap application with automation abilities.

Original languageEnglish
Title of host publication7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages79-84
Number of pages6
ISBN (Electronic)978-1-5090-2156-7
ISBN (Print)978-1-5090-2155-0
DOIs
Publication statusPublished - 23 Mar 2017
MoE publication typeA4 Article in a conference publication
Event7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Siem Reap, Cambodia
Duration: 1 Dec 20164 Dec 2016

Conference

Conference7th International Conference on Intelligent Control and Information Processing, ICICIP 2016
CountryCambodia
CitySiem Reap
Period1/12/164/12/16

Fingerprint

Hotelling's T2
Control Charts
Error Control
Solvent extraction
Prediction Error
Copper
Statistical process control
Multivariate Models
Univariate
Random errors
Multivariate Statistical Process Control
Systematic errors
Process monitoring
Statistical Process Control
Early Warning
Principal component analysis
Process Monitoring
Systematic Error
Random Error
Instrumentation

Keywords

  • Abnormal process behavior
  • Hotelling T
  • Normal operating conditions
  • Principal component analysis
  • Squared prediction error

Cite this

Filianin, K., Reinikainen, S. P., Sainio, T., Helaakoski, H., & Kyllonen, V. (2017). Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart. In 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings (pp. 79-84). [7885880] IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ICICIP.2016.7885880
Filianin, Kirill ; Reinikainen, Satu Pia ; Sainio, Tuomo ; Helaakoski, Heli ; Kyllonen, Vesa. / Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart. 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. IEEE Institute of Electrical and Electronic Engineers , 2017. pp. 79-84
@inproceedings{1ec1ac05bae4451881261fc0ffc6f26e,
title = "Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart",
abstract = "Once a multivariate model is developed, it can be combined with tools and techniques from univariate statistical process control to form multivariate statistical process control tools. It allows development of advanced process monitoring strategies. In the current study, copper plant history data with multiple variables was successfully treated by principal component analysis to detect abnormal process behavior, particularly, in copper solvent extraction. The multivariate model was based on the concentration levels of main process metals recorded by the industrial on-stream x-ray fluorescence analyzer. Normal operating conditions were defined through control limits that were assigned to Hotelling T2 values on x-axis and to squared prediction error values on y-axis. Samples that were beyond the limits were classified as either systematic or random errors, or outliers. Model testing showed successful application of control limits to detect abnormal behavior of copper solvent extraction process as early warnings. Compared to the conventional univariate techniques of analyzing one variable at a time, the proposed model allows to detect on-line a process failure summarizing information from all process variables simultaneously. The proposed methodology was combined with on-line quality monitoring tool developed by VTT, Technical Research Center of Finland, to visualize the results. Thus, the proposed approach has a potential in on-line industrial instrumentation providing fast, robust and cheap application with automation abilities.",
keywords = "Abnormal process behavior, Hotelling T, Normal operating conditions, Principal component analysis, Squared prediction error",
author = "Kirill Filianin and Reinikainen, {Satu Pia} and Tuomo Sainio and Heli Helaakoski and Vesa Kyllonen",
note = "Project code: 101074",
year = "2017",
month = "3",
day = "23",
doi = "10.1109/ICICIP.2016.7885880",
language = "English",
isbn = "978-1-5090-2155-0",
pages = "79--84",
booktitle = "7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Filianin, K, Reinikainen, SP, Sainio, T, Helaakoski, H & Kyllonen, V 2017, Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart. in 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings., 7885880, IEEE Institute of Electrical and Electronic Engineers , pp. 79-84, 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016, Siem Reap, Cambodia, 1/12/16. https://doi.org/10.1109/ICICIP.2016.7885880

Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart. / Filianin, Kirill; Reinikainen, Satu Pia; Sainio, Tuomo; Helaakoski, Heli; Kyllonen, Vesa.

7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. IEEE Institute of Electrical and Electronic Engineers , 2017. p. 79-84 7885880.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart

AU - Filianin, Kirill

AU - Reinikainen, Satu Pia

AU - Sainio, Tuomo

AU - Helaakoski, Heli

AU - Kyllonen, Vesa

N1 - Project code: 101074

PY - 2017/3/23

Y1 - 2017/3/23

N2 - Once a multivariate model is developed, it can be combined with tools and techniques from univariate statistical process control to form multivariate statistical process control tools. It allows development of advanced process monitoring strategies. In the current study, copper plant history data with multiple variables was successfully treated by principal component analysis to detect abnormal process behavior, particularly, in copper solvent extraction. The multivariate model was based on the concentration levels of main process metals recorded by the industrial on-stream x-ray fluorescence analyzer. Normal operating conditions were defined through control limits that were assigned to Hotelling T2 values on x-axis and to squared prediction error values on y-axis. Samples that were beyond the limits were classified as either systematic or random errors, or outliers. Model testing showed successful application of control limits to detect abnormal behavior of copper solvent extraction process as early warnings. Compared to the conventional univariate techniques of analyzing one variable at a time, the proposed model allows to detect on-line a process failure summarizing information from all process variables simultaneously. The proposed methodology was combined with on-line quality monitoring tool developed by VTT, Technical Research Center of Finland, to visualize the results. Thus, the proposed approach has a potential in on-line industrial instrumentation providing fast, robust and cheap application with automation abilities.

AB - Once a multivariate model is developed, it can be combined with tools and techniques from univariate statistical process control to form multivariate statistical process control tools. It allows development of advanced process monitoring strategies. In the current study, copper plant history data with multiple variables was successfully treated by principal component analysis to detect abnormal process behavior, particularly, in copper solvent extraction. The multivariate model was based on the concentration levels of main process metals recorded by the industrial on-stream x-ray fluorescence analyzer. Normal operating conditions were defined through control limits that were assigned to Hotelling T2 values on x-axis and to squared prediction error values on y-axis. Samples that were beyond the limits were classified as either systematic or random errors, or outliers. Model testing showed successful application of control limits to detect abnormal behavior of copper solvent extraction process as early warnings. Compared to the conventional univariate techniques of analyzing one variable at a time, the proposed model allows to detect on-line a process failure summarizing information from all process variables simultaneously. The proposed methodology was combined with on-line quality monitoring tool developed by VTT, Technical Research Center of Finland, to visualize the results. Thus, the proposed approach has a potential in on-line industrial instrumentation providing fast, robust and cheap application with automation abilities.

KW - Abnormal process behavior

KW - Hotelling T

KW - Normal operating conditions

KW - Principal component analysis

KW - Squared prediction error

UR - http://www.scopus.com/inward/record.url?scp=85018176355&partnerID=8YFLogxK

U2 - 10.1109/ICICIP.2016.7885880

DO - 10.1109/ICICIP.2016.7885880

M3 - Conference article in proceedings

AN - SCOPUS:85018176355

SN - 978-1-5090-2155-0

SP - 79

EP - 84

BT - 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Filianin K, Reinikainen SP, Sainio T, Helaakoski H, Kyllonen V. Detection of abnormal process behavior in copper solvent extraction by Hotelling T2 and squared prediction error control chart. In 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. IEEE Institute of Electrical and Electronic Engineers . 2017. p. 79-84. 7885880 https://doi.org/10.1109/ICICIP.2016.7885880