Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Cyber-physical LPG debutanizer distillation columns: machine-learning-based soft sensors for product quality monitoring

Rožanec Jože Martin, Trajkova Elena, Lu Jinzhi, Sarantinoudis Nikolaos, Arampatzis Georgios, Eirinakis Pavlos, Mourtos Ioannis, Onat Melike K., Yilmaz Deren A., Košmerlj Aljaž, Kenda Klemen, Fortuna Blaz, Mladenic Dunja

Simple record

URIhttp://purl.tuc.gr/dl/dias/0166077B-94B2-467A-9543-62A0430A7B4A-
Identifierhttps://doi.org/10.3390/app112411790-
Identifierhttps://www.mdpi.com/2076-3417/11/24/11790/htm-
Languageen-
Extent26 pagesen
TitleCyber-physical LPG debutanizer distillation columns: machine-learning-based soft sensors for product quality monitoringen
CreatorRožanec Jože Martinen
CreatorTrajkova Elenaen
CreatorLu Jinzhien
CreatorSarantinoudis Nikolaosen
CreatorΣαραντινουδης Νικολαοςel
CreatorArampatzis Georgiosen
CreatorΑραμπατζης Γεωργιοςel
CreatorEirinakis Pavlosen
CreatorMourtos Ioannisen
CreatorOnat Melike K.en
CreatorYilmaz Deren A.en
CreatorKošmerlj Aljažen
CreatorKenda Klemenen
CreatorFortuna Blazen
CreatorMladenic Dunjaen
PublisherMDPIen
Content SummaryRefineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predictive machine learning models, enables the provision of equipment state monitoring services and the generation of decision-making for equipment operations. In this paper, we propose two machine learning models: (1) to forecast the amount of pentane (C5) content in the final product mixture; (2) to identify if C5 content exceeds the specification thresholds for the final product quality. We validate our approach using a use case from a real-world refinery. In addition, we develop a visualization to assess which features are considered most important during feature selection, and later by the machine learning models. Finally, we provide insights on the sensor values in the dataset, which help to identify the operational conditions for using such machine learning models. en
Type of ItemPeer-Reviewed Journal Publicationen
Type of ItemΔημοσίευση σε Περιοδικό με Κριτέςel
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2022-09-20-
Date of Publication2021-
SubjectArtificial intelligenceen
SubjectExplainable artificial intelligenceen
SubjectIndustry 4.0en
SubjectSmart manufacturingen
SubjectCrude oil distillationen
SubjectDebutanizationen
SubjectLPG purificationen
Bibliographic CitationJ. M. Rožanec, E. Trajkova, J. Lu, N. Sarantinoudis, G. Arampatzis, P. Eirinakis, I. Mourtos, M. K. Onat, D. A. Yilmaz, A. Košmerlj, K. Kenda, B. Fortuna, and D. Mladenić, “Cyber-physical LPG debutanizer distillation columns: machine-learning-based soft sensors for product quality monitoring,” Appl. Sci., vol. 11, no. 24, Dec. 2021, doi: 10.3390/app112411790.en

Available Files

Services

Statistics

 

Copyright © DIAS 2013