A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment

Maximilian O. Besenhard, Otto Scheibelhofer, Kjell François, Martin Joksch, Barbara Kavsek

Research output: Contribution to journalArticleResearchpeer-review

Abstract

This work describes a multivariate monitoring and control concept for bioprocesses based on historical process data. The concept is demonstrated for a Saccharomyces Cerevisiae (baker’s yeast) fermentation process executed in a small-scale bioreactor, which is equipped with common probes to analyze the broth and off-gases. The data of “in-control” fermentation processes were evaluated by means of a principal component analysis to define confidence limits for subsequent fermentations. A violation of these limits indicated that a process had to be classified as “out-of-control”. Fault diagnosis was provided by the components of the squared prediction error, which can also be used to determine the appropriate counteractions, e.g. via an expert system control strategy as described in this study. The sensitivity of fault diagnosis was demonstrated via various erroneous runs. The duration of bioprocesses can vary distinctly, which complicates the definition of time dependent control limits. Therefore, this study utilizes a three-component partial least squares regression model to quantify the current batch maturity during the process. This maturity is then used to reference current data to the appropriate historical data and the assigned control limits.

Original languageEnglish
Pages (from-to)1501-1514
Number of pages14
JournalJournal of Intelligent Manufacturing
Volume29
Issue number7
DOIs
Publication statusPublished - 1 Oct 2018

Fingerprint

Fermenters
Process monitoring
Process control
Fermentation
Yeast
Failure analysis
Bioreactors
Principal component analysis
Expert systems
Monitoring
Gases

Keywords

  • Automated fault diagnostic
  • Fermentation
  • maturity
  • Multivariate process monitoring
  • PCA
  • PLS

ASJC Scopus subject areas

  • Software
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Cite this

A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment. / Besenhard, Maximilian O.; Scheibelhofer, Otto; François, Kjell; Joksch, Martin; Kavsek, Barbara.

In: Journal of Intelligent Manufacturing, Vol. 29, No. 7, 01.10.2018, p. 1501-1514.

Research output: Contribution to journalArticleResearchpeer-review

Besenhard, Maximilian O. ; Scheibelhofer, Otto ; François, Kjell ; Joksch, Martin ; Kavsek, Barbara. / A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment. In: Journal of Intelligent Manufacturing. 2018 ; Vol. 29, No. 7. pp. 1501-1514.
@article{35412a56d84b4676a64252e0bf814e09,
title = "A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment",
abstract = "This work describes a multivariate monitoring and control concept for bioprocesses based on historical process data. The concept is demonstrated for a Saccharomyces Cerevisiae (baker’s yeast) fermentation process executed in a small-scale bioreactor, which is equipped with common probes to analyze the broth and off-gases. The data of “in-control” fermentation processes were evaluated by means of a principal component analysis to define confidence limits for subsequent fermentations. A violation of these limits indicated that a process had to be classified as “out-of-control”. Fault diagnosis was provided by the components of the squared prediction error, which can also be used to determine the appropriate counteractions, e.g. via an expert system control strategy as described in this study. The sensitivity of fault diagnosis was demonstrated via various erroneous runs. The duration of bioprocesses can vary distinctly, which complicates the definition of time dependent control limits. Therefore, this study utilizes a three-component partial least squares regression model to quantify the current batch maturity during the process. This maturity is then used to reference current data to the appropriate historical data and the assigned control limits.",
keywords = "Automated fault diagnostic, Fermentation, maturity, Multivariate process monitoring, PCA, PLS",
author = "Besenhard, {Maximilian O.} and Otto Scheibelhofer and Kjell Fran{\cc}ois and Martin Joksch and Barbara Kavsek",
year = "2018",
month = "10",
day = "1",
doi = "10.1007/s10845-015-1192-8",
language = "English",
volume = "29",
pages = "1501--1514",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Science + Business Media",
number = "7",

}

TY - JOUR

T1 - A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment

AU - Besenhard, Maximilian O.

AU - Scheibelhofer, Otto

AU - François, Kjell

AU - Joksch, Martin

AU - Kavsek, Barbara

PY - 2018/10/1

Y1 - 2018/10/1

N2 - This work describes a multivariate monitoring and control concept for bioprocesses based on historical process data. The concept is demonstrated for a Saccharomyces Cerevisiae (baker’s yeast) fermentation process executed in a small-scale bioreactor, which is equipped with common probes to analyze the broth and off-gases. The data of “in-control” fermentation processes were evaluated by means of a principal component analysis to define confidence limits for subsequent fermentations. A violation of these limits indicated that a process had to be classified as “out-of-control”. Fault diagnosis was provided by the components of the squared prediction error, which can also be used to determine the appropriate counteractions, e.g. via an expert system control strategy as described in this study. The sensitivity of fault diagnosis was demonstrated via various erroneous runs. The duration of bioprocesses can vary distinctly, which complicates the definition of time dependent control limits. Therefore, this study utilizes a three-component partial least squares regression model to quantify the current batch maturity during the process. This maturity is then used to reference current data to the appropriate historical data and the assigned control limits.

AB - This work describes a multivariate monitoring and control concept for bioprocesses based on historical process data. The concept is demonstrated for a Saccharomyces Cerevisiae (baker’s yeast) fermentation process executed in a small-scale bioreactor, which is equipped with common probes to analyze the broth and off-gases. The data of “in-control” fermentation processes were evaluated by means of a principal component analysis to define confidence limits for subsequent fermentations. A violation of these limits indicated that a process had to be classified as “out-of-control”. Fault diagnosis was provided by the components of the squared prediction error, which can also be used to determine the appropriate counteractions, e.g. via an expert system control strategy as described in this study. The sensitivity of fault diagnosis was demonstrated via various erroneous runs. The duration of bioprocesses can vary distinctly, which complicates the definition of time dependent control limits. Therefore, this study utilizes a three-component partial least squares regression model to quantify the current batch maturity during the process. This maturity is then used to reference current data to the appropriate historical data and the assigned control limits.

KW - Automated fault diagnostic

KW - Fermentation

KW - maturity

KW - Multivariate process monitoring

KW - PCA

KW - PLS

UR - http://www.scopus.com/inward/record.url?scp=84954569334&partnerID=8YFLogxK

U2 - 10.1007/s10845-015-1192-8

DO - 10.1007/s10845-015-1192-8

M3 - Article

VL - 29

SP - 1501

EP - 1514

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 7

ER -