Software sensor to enhance production of fructose

Research output: Contribution to journalArticle

Abstract

Present studies describe the on-line prediction of fructose concentration by using Artificial Neural Network (ANN) that employed as software sensor in the batch reactor for the biosynthesis of fructose by Immobilised Glucose Isomerase (IGI) of S.murinus. The process of fermentation was carried out in a 2-L batch bioreactor (New Brunswick Scientific, USA) with a working volume of 1.5 L reactor. All of the parameters were automatically controlled with the help of attached software. The optimum pH and temperature, for the production of fructose by Immmobilised Glucose Isomerase (IGI) of S.murinus were found to be 8 and 60 ° C, respectively. Accuracy of the proposed soft sensor was calculated by the correlation coefficient (R2) and mean square error (MSE). In this study, value R2 were greater than 0.95 and the values of MSE were less than 0.2, indicating a good fit of the ANN-soft sensor to the experimental data, accurate up to 95.7% for training and 100% for testing. Thus, the proposed ANN-soft sensor was the most precise in predicting fructose concentration.

Original languageEnglish
Pages (from-to)158-166
Number of pages9
JournalModern Applied Science
Volume8
Issue number3
DOIs
Publication statusPublished - 2014

Fingerprint

Fructose
Sensors
Neural networks
Mean square error
Glucose
Biosynthesis
Batch reactors
Bioreactors
Fermentation
Testing
Temperature

Keywords

  • Batch bioreactor
  • Fructose
  • Mean square error
  • On-line prediction

ASJC Scopus subject areas

  • General

Cite this

Software sensor to enhance production of fructose. / Abd Rahman, Norliza; Hussain, Mohd Azlan; Md Jahim, Jamaliah; Sheikh Abdullah, Siti Rozaimah.

In: Modern Applied Science, Vol. 8, No. 3, 2014, p. 158-166.

Research output: Contribution to journalArticle

@article{9e09e07041e9464ab450db5cc64f58fe,
title = "Software sensor to enhance production of fructose",
abstract = "Present studies describe the on-line prediction of fructose concentration by using Artificial Neural Network (ANN) that employed as software sensor in the batch reactor for the biosynthesis of fructose by Immobilised Glucose Isomerase (IGI) of S.murinus. The process of fermentation was carried out in a 2-L batch bioreactor (New Brunswick Scientific, USA) with a working volume of 1.5 L reactor. All of the parameters were automatically controlled with the help of attached software. The optimum pH and temperature, for the production of fructose by Immmobilised Glucose Isomerase (IGI) of S.murinus were found to be 8 and 60 ° C, respectively. Accuracy of the proposed soft sensor was calculated by the correlation coefficient (R2) and mean square error (MSE). In this study, value R2 were greater than 0.95 and the values of MSE were less than 0.2, indicating a good fit of the ANN-soft sensor to the experimental data, accurate up to 95.7{\%} for training and 100{\%} for testing. Thus, the proposed ANN-soft sensor was the most precise in predicting fructose concentration.",
keywords = "Batch bioreactor, Fructose, Mean square error, On-line prediction",
author = "{Abd Rahman}, Norliza and Hussain, {Mohd Azlan} and {Md Jahim}, Jamaliah and {Sheikh Abdullah}, {Siti Rozaimah}",
year = "2014",
doi = "10.5539/mas.v8n3p158",
language = "English",
volume = "8",
pages = "158--166",
journal = "Modern Applied Science",
issn = "1913-1844",
publisher = "Canadian Center of Science and Education",
number = "3",

}

TY - JOUR

T1 - Software sensor to enhance production of fructose

AU - Abd Rahman, Norliza

AU - Hussain, Mohd Azlan

AU - Md Jahim, Jamaliah

AU - Sheikh Abdullah, Siti Rozaimah

PY - 2014

Y1 - 2014

N2 - Present studies describe the on-line prediction of fructose concentration by using Artificial Neural Network (ANN) that employed as software sensor in the batch reactor for the biosynthesis of fructose by Immobilised Glucose Isomerase (IGI) of S.murinus. The process of fermentation was carried out in a 2-L batch bioreactor (New Brunswick Scientific, USA) with a working volume of 1.5 L reactor. All of the parameters were automatically controlled with the help of attached software. The optimum pH and temperature, for the production of fructose by Immmobilised Glucose Isomerase (IGI) of S.murinus were found to be 8 and 60 ° C, respectively. Accuracy of the proposed soft sensor was calculated by the correlation coefficient (R2) and mean square error (MSE). In this study, value R2 were greater than 0.95 and the values of MSE were less than 0.2, indicating a good fit of the ANN-soft sensor to the experimental data, accurate up to 95.7% for training and 100% for testing. Thus, the proposed ANN-soft sensor was the most precise in predicting fructose concentration.

AB - Present studies describe the on-line prediction of fructose concentration by using Artificial Neural Network (ANN) that employed as software sensor in the batch reactor for the biosynthesis of fructose by Immobilised Glucose Isomerase (IGI) of S.murinus. The process of fermentation was carried out in a 2-L batch bioreactor (New Brunswick Scientific, USA) with a working volume of 1.5 L reactor. All of the parameters were automatically controlled with the help of attached software. The optimum pH and temperature, for the production of fructose by Immmobilised Glucose Isomerase (IGI) of S.murinus were found to be 8 and 60 ° C, respectively. Accuracy of the proposed soft sensor was calculated by the correlation coefficient (R2) and mean square error (MSE). In this study, value R2 were greater than 0.95 and the values of MSE were less than 0.2, indicating a good fit of the ANN-soft sensor to the experimental data, accurate up to 95.7% for training and 100% for testing. Thus, the proposed ANN-soft sensor was the most precise in predicting fructose concentration.

KW - Batch bioreactor

KW - Fructose

KW - Mean square error

KW - On-line prediction

UR - http://www.scopus.com/inward/record.url?scp=84900398015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900398015&partnerID=8YFLogxK

U2 - 10.5539/mas.v8n3p158

DO - 10.5539/mas.v8n3p158

M3 - Article

AN - SCOPUS:84900398015

VL - 8

SP - 158

EP - 166

JO - Modern Applied Science

JF - Modern Applied Science

SN - 1913-1844

IS - 3

ER -