Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process

Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process

The paper deals with the problem of developing a multi-output soft sensor for the industrial reactive distillation process of methyl tert-butyl ether production. Unlike the existing soft sensor approaches, this paper proposes using a soft sensor with filters to predict model errors, which are then t...

Full description

Bibliographic Details
Main Authors: Vladimir Klimchenko, Andrei Torgashov, Yuri A. W. Shardt, Fan Yang
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Mathematics
Subjects:
soft sensing
multivariate filter
reactive distillation
Online Access:https://www.mdpi.com/2227-7390/9/16/1947
id doaj-2bf8eae4522146bcae239002511b8d11
record_format Article
spelling doaj-2bf8eae4522146bcae239002511b8d112021-08-26T14:02:21ZengMDPI AGMathematics2227-73902021-08-0191947194710.3390/math9161947Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation ProcessVladimir Klimchenko0Andrei Torgashov1Yuri A. W. Shardt2Fan Yang3Process Control Laboratory, Institute of Automation and Control Process FEB RAS, 5 Radio Str., Vladivostok 690041, RussiaProcess Control Laboratory, Institute of Automation and Control Process FEB RAS, 5 Radio Str., Vladivostok 690041, RussiaDepartment of Automation Engineering, Technical University of Ilmenau, 99084 Ilmenau, GermanyBeijing National Research Center for Information Science and Technology, Department of Automation, Tsinghua University, Beijing 100084, ChinaThe paper deals with the problem of developing a multi-output soft sensor for the industrial reactive distillation process of methyl tert-butyl ether production. Unlike the existing soft sensor approaches, this paper proposes using a soft sensor with filters to predict model errors, which are then taken into account as corrections in the final predictions of outputs. The decomposition of the problem of optimal estimation of time delays is proposed for each input of the soft sensor. Using the proposed approach to predict the concentrations of methyl sec-butyl ether, methanol, and the sum of dimers and trimers of isobutylene in the output product in a reactive distillation column was shown to improve the results by 32%, 67%, and 9.5%, respectively.https://www.mdpi.com/2227-7390/9/16/1947soft sensingmultivariate filterreactive distillation
collection DOAJ
language English
format Article
sources DOAJ
author Vladimir Klimchenko
Andrei Torgashov
Yuri A. W. Shardt
Fan Yang
spellingShingle Vladimir Klimchenko
Andrei Torgashov
Yuri A. W. Shardt
Fan Yang
Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
Mathematics
soft sensing
multivariate filter
reactive distillation
author_facet Vladimir Klimchenko
Andrei Torgashov
Yuri A. W. Shardt
Fan Yang
author_sort Vladimir Klimchenko
title Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
title_short Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
title_full Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
title_fullStr Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
title_full_unstemmed Multi-Output Soft Sensor with a Multivariate Filter That Predicts Errors Applied to an Industrial Reactive Distillation Process
title_sort multi-output soft sensor with a multivariate filter that predicts errors applied to an industrial reactive distillation process
publisher MDPI AG
series Mathematics
issn 2227-7390
publishDate 2021-08-01
description The paper deals with the problem of developing a multi-output soft sensor for the industrial reactive distillation process of methyl tert-butyl ether production. Unlike the existing soft sensor approaches, this paper proposes using a soft sensor with filters to predict model errors, which are then taken into account as corrections in the final predictions of outputs. The decomposition of the problem of optimal estimation of time delays is proposed for each input of the soft sensor. Using the proposed approach to predict the concentrations of methyl sec-butyl ether, methanol, and the sum of dimers and trimers of isobutylene in the output product in a reactive distillation column was shown to improve the results by 32%, 67%, and 9.5%, respectively.
topic soft sensing
multivariate filter
reactive distillation
url https://www.mdpi.com/2227-7390/9/16/1947
work_keys_str_mv AT vladimirklimchenko multioutputsoftsensorwithamultivariatefilterthatpredictserrorsappliedtoanindustrialreactivedistillationprocess
AT andreitorgashov multioutputsoftsensorwithamultivariatefilterthatpredictserrorsappliedtoanindustrialreactivedistillationprocess
AT yuriawshardt multioutputsoftsensorwithamultivariatefilterthatpredictserrorsappliedtoanindustrialreactivedistillationprocess
AT fanyang multioutputsoftsensorwithamultivariatefilterthatpredictserrorsappliedtoanindustrialreactivedistillationprocess
_version_ 1721191664583704576

Similar Items