Neural network predictive control by MIMS monitored 2,3-butanediol fermentation by Klebsiella oxytoca

Mei-Jywan Syu, Cheng L. Hou

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

With the aid of a membrane introduction mass spectrometer (MIMS), the major product 2,3-butanediol (2,3-BDL) as well as the other metabolites from the fermentation carried by Klebsiella oxytoca can be measured on-line simultaneously. A backpropagation neural network (BPN) being recognized with superior mapping ability was applied to this control study. This neural network adaptive control differs from those conventional controls for fermentation systems in which the measurements of cell mass and glucose are not included in the network model. It is only the measured product concentrations from the MIMS that are involved. Oxygen composition was chosen to be the control variable for this fermentation system. Oxygen composition was directly correlated to the measured product concentrations in the controller model. A two-dimensional (number of input nodes by number of data sets) moving window for on-line, dynamic learning of this fermentation system was applied. The input nodes of the network were also properly selected. Number of the training data sets for obtaining better control results was also determined empirically. Two control structures for this 2,3-BDL fermentation are discussed and compared in this work. The effect from adding time delay element to the network controller was also investigated.

Original languageEnglish
Pages (from-to)141-149
Number of pages9
JournalBioprocess Engineering
Volume21
Issue number2
DOIs
Publication statusPublished - 1999 Aug 26

Fingerprint

Klebsiella oxytoca
Mass spectrometers
Fermentation
Neural networks
Membranes
Oxygen
Aptitude
Controllers
Metabolites
Chemical analysis
Backpropagation
Glucose
2,3-butylene glycol
Learning
Time delay

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Applied Microbiology and Biotechnology

Cite this

@article{c9dbf6d84a82499f866f9bb6106ff98c,
title = "Neural network predictive control by MIMS monitored 2,3-butanediol fermentation by Klebsiella oxytoca",
abstract = "With the aid of a membrane introduction mass spectrometer (MIMS), the major product 2,3-butanediol (2,3-BDL) as well as the other metabolites from the fermentation carried by Klebsiella oxytoca can be measured on-line simultaneously. A backpropagation neural network (BPN) being recognized with superior mapping ability was applied to this control study. This neural network adaptive control differs from those conventional controls for fermentation systems in which the measurements of cell mass and glucose are not included in the network model. It is only the measured product concentrations from the MIMS that are involved. Oxygen composition was chosen to be the control variable for this fermentation system. Oxygen composition was directly correlated to the measured product concentrations in the controller model. A two-dimensional (number of input nodes by number of data sets) moving window for on-line, dynamic learning of this fermentation system was applied. The input nodes of the network were also properly selected. Number of the training data sets for obtaining better control results was also determined empirically. Two control structures for this 2,3-BDL fermentation are discussed and compared in this work. The effect from adding time delay element to the network controller was also investigated.",
author = "Mei-Jywan Syu and Hou, {Cheng L.}",
year = "1999",
month = "8",
day = "26",
doi = "10.1007/s004490050654",
language = "English",
volume = "21",
pages = "141--149",
journal = "Bioprocess and Biosystems Engineering",
issn = "1615-7591",
publisher = "Springer Verlag",
number = "2",

}

Neural network predictive control by MIMS monitored 2,3-butanediol fermentation by Klebsiella oxytoca. / Syu, Mei-Jywan; Hou, Cheng L.

In: Bioprocess Engineering, Vol. 21, No. 2, 26.08.1999, p. 141-149.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network predictive control by MIMS monitored 2,3-butanediol fermentation by Klebsiella oxytoca

AU - Syu, Mei-Jywan

AU - Hou, Cheng L.

PY - 1999/8/26

Y1 - 1999/8/26

N2 - With the aid of a membrane introduction mass spectrometer (MIMS), the major product 2,3-butanediol (2,3-BDL) as well as the other metabolites from the fermentation carried by Klebsiella oxytoca can be measured on-line simultaneously. A backpropagation neural network (BPN) being recognized with superior mapping ability was applied to this control study. This neural network adaptive control differs from those conventional controls for fermentation systems in which the measurements of cell mass and glucose are not included in the network model. It is only the measured product concentrations from the MIMS that are involved. Oxygen composition was chosen to be the control variable for this fermentation system. Oxygen composition was directly correlated to the measured product concentrations in the controller model. A two-dimensional (number of input nodes by number of data sets) moving window for on-line, dynamic learning of this fermentation system was applied. The input nodes of the network were also properly selected. Number of the training data sets for obtaining better control results was also determined empirically. Two control structures for this 2,3-BDL fermentation are discussed and compared in this work. The effect from adding time delay element to the network controller was also investigated.

AB - With the aid of a membrane introduction mass spectrometer (MIMS), the major product 2,3-butanediol (2,3-BDL) as well as the other metabolites from the fermentation carried by Klebsiella oxytoca can be measured on-line simultaneously. A backpropagation neural network (BPN) being recognized with superior mapping ability was applied to this control study. This neural network adaptive control differs from those conventional controls for fermentation systems in which the measurements of cell mass and glucose are not included in the network model. It is only the measured product concentrations from the MIMS that are involved. Oxygen composition was chosen to be the control variable for this fermentation system. Oxygen composition was directly correlated to the measured product concentrations in the controller model. A two-dimensional (number of input nodes by number of data sets) moving window for on-line, dynamic learning of this fermentation system was applied. The input nodes of the network were also properly selected. Number of the training data sets for obtaining better control results was also determined empirically. Two control structures for this 2,3-BDL fermentation are discussed and compared in this work. The effect from adding time delay element to the network controller was also investigated.

UR - http://www.scopus.com/inward/record.url?scp=0032775899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032775899&partnerID=8YFLogxK

U2 - 10.1007/s004490050654

DO - 10.1007/s004490050654

M3 - Article

VL - 21

SP - 141

EP - 149

JO - Bioprocess and Biosystems Engineering

JF - Bioprocess and Biosystems Engineering

SN - 1615-7591

IS - 2

ER -