Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process
Erythromycin fermentation process is a typical microbial fermentation process. Soft sensors can be used to estimate biomass of Erythromycin fermentation process for their relative low cost, simple development, and ability to predict difficult-to-measure variables. However, traditional soft...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Association of the Chemical Engineers of Serbia
2016-01-01
|
Series: | Chemical Industry and Chemical Engineering Quarterly |
Subjects: | |
Online Access: | http://www.doiserbia.nb.rs/img/doi/1451-9372/2016/1451-93721500026M.pdf |
id |
doaj-f09ccc9f4a6c41c38a8a264b8559e3a9 |
---|---|
record_format |
Article |
spelling |
doaj-f09ccc9f4a6c41c38a8a264b8559e3a92020-11-25T00:15:33ZengAssociation of the Chemical Engineers of SerbiaChemical Industry and Chemical Engineering Quarterly1451-93722217-74342016-01-0122212713510.2298/CICEQ150125026M1451-93721500026MSoft sensor based on Gaussian process regression and its application in erythromycin fermentation processMei Congli0Yang Ming1Shu Dongxin2Jiang Hui3Liu Guohai4Liao Zhiling5Jiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaJiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaJiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaJiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaJiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaJiangsu University, School of Electrical and Information Engineering, Zhenjiang, PR ChinaErythromycin fermentation process is a typical microbial fermentation process. Soft sensors can be used to estimate biomass of Erythromycin fermentation process for their relative low cost, simple development, and ability to predict difficult-to-measure variables. However, traditional soft sensors, e.g. artificial neural network (ANN) soft sensors, support vector machine (SVM) soft sensors, etc., cannot represent the uncertainty (measurement precision) of outputs. That results in difficulties in practice. Gaussian process regression (GPR) provides a novel framework to solve regression problems. The output uncertainty of a GPR model follows Gaussian distribution, expressed in terms of mean and variance. The mean represents the predicted output. The variance can be viewed as the measure of confidence in the predicted output that distinguishes the GPR from NN and SVM soft sensor models. We proposed a systematic approach based on GPR and principal component analysis (PCA) to establish a soft sensor to estimate biomass of Erythromycin fermentation process. Simulations on industrial data from an Erythromycin fermentation process show the proposed GPR soft sensor has high performance of modeling the uncertainty of estimates.http://www.doiserbia.nb.rs/img/doi/1451-9372/2016/1451-93721500026M.pdffermentation processsoft sensoruncertainlyGaussian process regressionprinciple component analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mei Congli Yang Ming Shu Dongxin Jiang Hui Liu Guohai Liao Zhiling |
spellingShingle |
Mei Congli Yang Ming Shu Dongxin Jiang Hui Liu Guohai Liao Zhiling Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process Chemical Industry and Chemical Engineering Quarterly fermentation process soft sensor uncertainly Gaussian process regression principle component analysis |
author_facet |
Mei Congli Yang Ming Shu Dongxin Jiang Hui Liu Guohai Liao Zhiling |
author_sort |
Mei Congli |
title |
Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process |
title_short |
Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process |
title_full |
Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process |
title_fullStr |
Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process |
title_full_unstemmed |
Soft sensor based on Gaussian process regression and its application in erythromycin fermentation process |
title_sort |
soft sensor based on gaussian process regression and its application in erythromycin fermentation process |
publisher |
Association of the Chemical Engineers of Serbia |
series |
Chemical Industry and Chemical Engineering Quarterly |
issn |
1451-9372 2217-7434 |
publishDate |
2016-01-01 |
description |
Erythromycin fermentation process is a typical microbial fermentation
process. Soft sensors can be used to estimate biomass of Erythromycin
fermentation process for their relative low cost, simple development, and
ability to predict difficult-to-measure variables. However, traditional soft
sensors, e.g. artificial neural network (ANN) soft sensors, support vector
machine (SVM) soft sensors, etc., cannot represent the uncertainty
(measurement precision) of outputs. That results in difficulties in practice.
Gaussian process regression (GPR) provides a novel framework to solve
regression problems. The output uncertainty of a GPR model follows Gaussian
distribution, expressed in terms of mean and variance. The mean represents
the predicted output. The variance can be viewed as the measure of confidence
in the predicted output that distinguishes the GPR from NN and SVM soft
sensor models. We proposed a systematic approach based on GPR and principal
component analysis (PCA) to establish a soft sensor to estimate biomass of
Erythromycin fermentation process. Simulations on industrial data from an
Erythromycin fermentation process show the proposed GPR soft sensor has high
performance of modeling the uncertainty of estimates. |
topic |
fermentation process soft sensor uncertainly Gaussian process regression principle component analysis |
url |
http://www.doiserbia.nb.rs/img/doi/1451-9372/2016/1451-93721500026M.pdf |
work_keys_str_mv |
AT meicongli softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess AT yangming softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess AT shudongxin softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess AT jianghui softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess AT liuguohai softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess AT liaozhiling softsensorbasedongaussianprocessregressionanditsapplicationinerythromycinfermentationprocess |
_version_ |
1725386256379019264 |