Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes

Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes

Just-in-time learning (JITL) has been used to construct soft sensor models online for its ability of handling strong nonlinearity and changes in processes. The most key procedure in JITL modelling is selecting relevant samples similar to a query sample. However, the common similarity criterions used...

Full description

Bibliographic Details
Main Authors: C. Mei, Y. Chen, H. Jiang, Y. Ding, X. Chen, G. Liu
Format: Article
Language:English
Published: AIDIC Servizi S.r.l. 2017-10-01
Series:Chemical Engineering Transactions
Online Access:https://www.cetjournal.it/index.php/cet/article/view/225
id doaj-86c46fb762d34d6481c28d28dbb93dc3
record_format Article
spelling doaj-86c46fb762d34d6481c28d28dbb93dc32021-02-17T21:24:07ZengAIDIC Servizi S.r.l.Chemical Engineering Transactions2283-92162017-10-016110.3303/CET1761172Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes C. MeiY. ChenH. JiangY. DingX. ChenG. LiuJust-in-time learning (JITL) has been used to construct soft sensor models online for its ability of handling strong nonlinearity and changes in processes. The most key procedure in JITL modelling is selecting relevant samples similar to a query sample. However, the common similarity criterions used to select relevant samples do not always function well for only considering the similarity of input data. Large noise or outliers in output data may result in inappropriate predictions of JITL based soft sensors. In this work, a combination of similarity measures, the conventional similarity of input and a novel similarity of output, is proposed for comprehensively understanding and selecting relevant samples. The effectiveness of the proposed soft sensor is demonstrated through an industrial fed-batch Erythromycin fermentation process. https://www.cetjournal.it/index.php/cet/article/view/225
collection DOAJ
language English
format Article
sources DOAJ
author C. Mei
Y. Chen
H. Jiang
Y. Ding
X. Chen
G. Liu
spellingShingle C. Mei
Y. Chen
H. Jiang
Y. Ding
X. Chen
G. Liu
Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
Chemical Engineering Transactions
author_facet C. Mei
Y. Chen
H. Jiang
Y. Ding
X. Chen
G. Liu
author_sort C. Mei
title Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
title_short Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
title_full Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
title_fullStr Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
title_full_unstemmed Just-in-time Modeling with a Combination of Input and Output Similarity Criterions for Soft Sensor Modeling in Fermentation Processes
title_sort just-in-time modeling with a combination of input and output similarity criterions for soft sensor modeling in fermentation processes
publisher AIDIC Servizi S.r.l.
series Chemical Engineering Transactions
issn 2283-9216
publishDate 2017-10-01
description Just-in-time learning (JITL) has been used to construct soft sensor models online for its ability of handling strong nonlinearity and changes in processes. The most key procedure in JITL modelling is selecting relevant samples similar to a query sample. However, the common similarity criterions used to select relevant samples do not always function well for only considering the similarity of input data. Large noise or outliers in output data may result in inappropriate predictions of JITL based soft sensors. In this work, a combination of similarity measures, the conventional similarity of input and a novel similarity of output, is proposed for comprehensively understanding and selecting relevant samples. The effectiveness of the proposed soft sensor is demonstrated through an industrial fed-batch Erythromycin fermentation process.
url https://www.cetjournal.it/index.php/cet/article/view/225
work_keys_str_mv AT cmei justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
AT ychen justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
AT hjiang justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
AT yding justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
AT xchen justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
AT gliu justintimemodelingwithacombinationofinputandoutputsimilaritycriterionsforsoftsensormodelinginfermentationprocesses
_version_ 1724264169143795712

Similar Items