Monitoring biological processes using univariate statistical process control

Majdi Mansouri, Ayman Al-Khazraji, Sin Yin Teh, Mohamed Faouzi Harkat, Hazem Nounou, Mohamed Nounou

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Biological modelling is a challenging task specifically when state variables are difficult or even impossible to be measured. Consequently, monitoring quality of biological process will be impacted negatively due to the lack of an accurate model capable of reflecting precisely the process dynamics. Moreover, the faults in such systems cannot be detected robustly. The current work proposes a novel approach that combines state estimation with process monitoring techniques. The developed approach, named as particle filter (PF)'based multiscale maximum double exponentially weighted moving average (MS-M-DEWMA) chart, includes two main phases. In the first phase, the PF technique is applied to estimate the unknown nonlinear states of the biological processes. In the second phase, the statistical univariate chart, MS-M-DEWMA is adopted to address fault detection in biological processes. Therefore, in this work, we propose a monitoring approach capable of detecting shifts in mean and/or variance in biological systems (pre-defined structure obtained using material and energy balances) where the variables are estimated using state estimation techniques. The detection chart MS-M-DEWMA is applied to the residuals computed using the PF. The advantages of PF-based MS-M-DEWMA method are threefold: (i) extract features and decorrelate measurements using dynamical multiscale representation; (ii) estimate the state of nonlinear biological processes using the PF technique; and (iii) enhance monitoring of biological processes through detecting shifts of both variance and mean using MS-M-DEWMA chart. The proposed approach is validated using a Cad system in E. coli (CSEC) model.

Original languageEnglish
JournalCanadian Journal of Chemical Engineering
DOIs
Publication statusAccepted/In press - 1 Jan 2018

Fingerprint

Statistical process control
State estimation
Monitoring
Process monitoring
Biological systems
Energy balance
Fault detection
Escherichia coli

Keywords

  • Biological processes
  • exponentially weighted moving average
  • fault detection
  • particle filtering

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Monitoring biological processes using univariate statistical process control. / Mansouri, Majdi; Al-Khazraji, Ayman; Yin Teh, Sin; Harkat, Mohamed Faouzi; Nounou, Hazem; Nounou, Mohamed.

In: Canadian Journal of Chemical Engineering, 01.01.2018.

Research output: Contribution to journalArticle

@article{dc0dd7f62c404336b56760b99a44b8fc,
title = "Monitoring biological processes using univariate statistical process control",
abstract = "Biological modelling is a challenging task specifically when state variables are difficult or even impossible to be measured. Consequently, monitoring quality of biological process will be impacted negatively due to the lack of an accurate model capable of reflecting precisely the process dynamics. Moreover, the faults in such systems cannot be detected robustly. The current work proposes a novel approach that combines state estimation with process monitoring techniques. The developed approach, named as particle filter (PF)'based multiscale maximum double exponentially weighted moving average (MS-M-DEWMA) chart, includes two main phases. In the first phase, the PF technique is applied to estimate the unknown nonlinear states of the biological processes. In the second phase, the statistical univariate chart, MS-M-DEWMA is adopted to address fault detection in biological processes. Therefore, in this work, we propose a monitoring approach capable of detecting shifts in mean and/or variance in biological systems (pre-defined structure obtained using material and energy balances) where the variables are estimated using state estimation techniques. The detection chart MS-M-DEWMA is applied to the residuals computed using the PF. The advantages of PF-based MS-M-DEWMA method are threefold: (i) extract features and decorrelate measurements using dynamical multiscale representation; (ii) estimate the state of nonlinear biological processes using the PF technique; and (iii) enhance monitoring of biological processes through detecting shifts of both variance and mean using MS-M-DEWMA chart. The proposed approach is validated using a Cad system in E. coli (CSEC) model.",
keywords = "Biological processes, exponentially weighted moving average, fault detection, particle filtering",
author = "Majdi Mansouri and Ayman Al-Khazraji and {Yin Teh}, Sin and Harkat, {Mohamed Faouzi} and Hazem Nounou and Mohamed Nounou",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/cjce.23310",
language = "English",
journal = "Canadian Journal of Chemical Engineering",
issn = "0008-4034",
publisher = "Wiley-Liss Inc.",

}

TY - JOUR

T1 - Monitoring biological processes using univariate statistical process control

AU - Mansouri, Majdi

AU - Al-Khazraji, Ayman

AU - Yin Teh, Sin

AU - Harkat, Mohamed Faouzi

AU - Nounou, Hazem

AU - Nounou, Mohamed

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Biological modelling is a challenging task specifically when state variables are difficult or even impossible to be measured. Consequently, monitoring quality of biological process will be impacted negatively due to the lack of an accurate model capable of reflecting precisely the process dynamics. Moreover, the faults in such systems cannot be detected robustly. The current work proposes a novel approach that combines state estimation with process monitoring techniques. The developed approach, named as particle filter (PF)'based multiscale maximum double exponentially weighted moving average (MS-M-DEWMA) chart, includes two main phases. In the first phase, the PF technique is applied to estimate the unknown nonlinear states of the biological processes. In the second phase, the statistical univariate chart, MS-M-DEWMA is adopted to address fault detection in biological processes. Therefore, in this work, we propose a monitoring approach capable of detecting shifts in mean and/or variance in biological systems (pre-defined structure obtained using material and energy balances) where the variables are estimated using state estimation techniques. The detection chart MS-M-DEWMA is applied to the residuals computed using the PF. The advantages of PF-based MS-M-DEWMA method are threefold: (i) extract features and decorrelate measurements using dynamical multiscale representation; (ii) estimate the state of nonlinear biological processes using the PF technique; and (iii) enhance monitoring of biological processes through detecting shifts of both variance and mean using MS-M-DEWMA chart. The proposed approach is validated using a Cad system in E. coli (CSEC) model.

AB - Biological modelling is a challenging task specifically when state variables are difficult or even impossible to be measured. Consequently, monitoring quality of biological process will be impacted negatively due to the lack of an accurate model capable of reflecting precisely the process dynamics. Moreover, the faults in such systems cannot be detected robustly. The current work proposes a novel approach that combines state estimation with process monitoring techniques. The developed approach, named as particle filter (PF)'based multiscale maximum double exponentially weighted moving average (MS-M-DEWMA) chart, includes two main phases. In the first phase, the PF technique is applied to estimate the unknown nonlinear states of the biological processes. In the second phase, the statistical univariate chart, MS-M-DEWMA is adopted to address fault detection in biological processes. Therefore, in this work, we propose a monitoring approach capable of detecting shifts in mean and/or variance in biological systems (pre-defined structure obtained using material and energy balances) where the variables are estimated using state estimation techniques. The detection chart MS-M-DEWMA is applied to the residuals computed using the PF. The advantages of PF-based MS-M-DEWMA method are threefold: (i) extract features and decorrelate measurements using dynamical multiscale representation; (ii) estimate the state of nonlinear biological processes using the PF technique; and (iii) enhance monitoring of biological processes through detecting shifts of both variance and mean using MS-M-DEWMA chart. The proposed approach is validated using a Cad system in E. coli (CSEC) model.

KW - Biological processes

KW - exponentially weighted moving average

KW - fault detection

KW - particle filtering

UR - http://www.scopus.com/inward/record.url?scp=85055167007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055167007&partnerID=8YFLogxK

U2 - 10.1002/cjce.23310

DO - 10.1002/cjce.23310

M3 - Article

JO - Canadian Journal of Chemical Engineering

JF - Canadian Journal of Chemical Engineering

SN - 0008-4034

ER -