A Bayesian inferential sensor for predicting the reactant concentration in an exothermic chemical process
dc.contributor | Aalto-yliopisto | fi |
dc.contributor | Aalto University | en |
dc.contributor.author | Ikonen, Teemu | en_US |
dc.contributor.author | Bergman, Samuli | en_US |
dc.contributor.author | Corona, Francesco | en_US |
dc.contributor.department | Department of Chemical and Metallurgical Engineering | en |
dc.contributor.groupauthor | Process Control and Automation | en |
dc.contributor.organization | Neste Corporation | en_US |
dc.date.accessioned | 2023-10-11T09:35:42Z | |
dc.date.available | 2023-10-11T09:35:42Z | |
dc.date.issued | 2023-10-15 | en_US |
dc.description | We wish to thank Akshaya Athwale, Kristian Bergman, Cesar de Araujo Filho, Muhammad Emzir, Katsiaryna Haitsiukevich, Sakira Hassan, Alexander Ilin, Viljami Iso-Markku, James Kabugo, Sanna Laitinen, Amir Shirdel, Simo Särkkä, Stefan Tötterman for fruitful discussions and insight on the process of catalytic hydrogenation. We acknowledge the financial support from the Academy of Finland through project RELOOP (decision number 330388). | |
dc.description.abstract | In many chemical reactors, concentration measurements are conducted off-line in a laboratory, which involve manual work and can therefore be conducted only infrequently. We propose a Bayesian inferential sensor to predict the reactant concentration in the inlet stream of an exothermic chemical process. The inferential sensor is based on the Bayesian inverse approach and the autoregressive integrated moving average (ARIMA) model. It enables the prediction of the reactant concentration at the frequency of automated on-line measurements, which is typically much higher than that of laboratory measurements. We demonstrate the method on real industrial process data from catalytic hydrogenation of aromatic compounds. The predicted aromatics concentration in the inlet stream, generated based on the latest on-line measurements and two-week-old laboratory data, has a coefficient of determination of 0.936 and a root mean square error of 0.654 mass-%. | en |
dc.description.version | Peer reviewed | en |
dc.format.extent | 10 | |
dc.format.mimetype | application/pdf | en_US |
dc.identifier.citation | Ikonen, T, Bergman, S & Corona, F 2023, 'A Bayesian inferential sensor for predicting the reactant concentration in an exothermic chemical process', Chemometrics and Intelligent Laboratory Systems, vol. 241, 104942. https://doi.org/10.1016/j.chemolab.2023.104942 | en |
dc.identifier.doi | 10.1016/j.chemolab.2023.104942 | en_US |
dc.identifier.issn | 0169-7439 | |
dc.identifier.issn | 1873-3239 | |
dc.identifier.other | PURE UUID: 8af433d1-6744-4106-bd8c-c4cb8ca0fcd3 | en_US |
dc.identifier.other | PURE ITEMURL: https://research.aalto.fi/en/publications/8af433d1-6744-4106-bd8c-c4cb8ca0fcd3 | en_US |
dc.identifier.other | PURE LINK: http://www.scopus.com/inward/record.url?scp=85170432704&partnerID=8YFLogxK | |
dc.identifier.other | PURE FILEURL: https://research.aalto.fi/files/123819174/CHEM_Ikonen_et_al_A_Bayesian_inferential_2023_Chemometrics_and_Intelligent_Laboratory_Systems.pdf | en_US |
dc.identifier.uri | https://aaltodoc.aalto.fi/handle/123456789/123919 | |
dc.identifier.urn | URN:NBN:fi:aalto-202310116266 | |
dc.language.iso | en | en |
dc.publisher | Elsevier | |
dc.relation.ispartofseries | Chemometrics and Intelligent Laboratory Systems | en |
dc.relation.ispartofseries | Volume 241 | en |
dc.rights | openAccess | en |
dc.subject.keyword | inferential sensor | en_US |
dc.subject.keyword | Bayesian analysis | en_US |
dc.subject.keyword | ARIMA | en_US |
dc.subject.keyword | exothermic process | en_US |
dc.subject.keyword | concentration | en_US |
dc.title | A Bayesian inferential sensor for predicting the reactant concentration in an exothermic chemical process | en |
dc.type | A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä | fi |
dc.type.version | publishedVersion |