Data-driven degradation model for batch processes: a case study on heat exchanger fouling
| dc.contributor.author | Wu, Ouyang | |
| dc.contributor.author | Bouaswaig, Ala | |
| dc.contributor.author | Schneider, Stefan | |
| dc.contributor.author | Leira, Fernando | |
| dc.contributor.author | Imsland, Lars Struen | |
| dc.contributor.author | Roth, Matthias | |
| dc.date.accessioned | 2019-04-01T12:11:49Z | |
| dc.date.available | 2019-04-01T12:11:49Z | |
| dc.date.created | 2019-01-13T19:28:43Z | |
| dc.date.issued | 2018 | |
| dc.identifier.citation | Computer-aided chemical engineering. 2018, 43 139-144. | nb_NO |
| dc.identifier.issn | 1570-7946 | |
| dc.identifier.uri | http://hdl.handle.net/11250/2592719 | |
| dc.language.iso | eng | nb_NO |
| dc.subject | In this paper, we present an industrial case study of a batch process; the degradation effect is fouling in heat exchangers which impedes heat transfer and fluid flow during batch production. The degradation increases from batch to batch until the batch reactor is shut down for a scheduled maintenance. That is, there is a periodic pattern in the batch-to-batch data as a result of the degradation. We propose a novel data-driven modeling technique for predicting the evolution of a batch degradation key performance indicator (KPI). This method extends existing algorithms (based on partial least squares, PLS) for the treatment of within-batch data to the present batch-to-batch degradation problem. An existing missing data algorithm for PLS models is employed to predict degradation in future batches. The proposed approach is then applied to the case study, and predicts the evolution of the fouling KPI with respect to the production planning under predefined process operations, which is a basis for optimal scheduling of batch production and maintenance. | nb_NO |
| dc.title | Data-driven degradation model for batch processes: a case study on heat exchanger fouling | nb_NO |
| dc.type | Journal article | nb_NO |
| dc.type | Peer reviewed | nb_NO |
| dc.description.version | acceptedVersion | nb_NO |
| dc.source.pagenumber | 139-144 | nb_NO |
| dc.source.volume | 43 | nb_NO |
| dc.source.journal | Computer-aided chemical engineering | nb_NO |
| dc.identifier.doi | https://doi.org/10.1016/B978-0-444-64235-6.50026-7 | |
| dc.identifier.cristin | 1655707 | |
| dc.relation.project | EU/675215 | nb_NO |
| dc.description.localcode | This chapter will not be available due to copyright restrictions. Copyright © 2018 Elsevier B.V. All rights reserved. | nb_NO |
| cristin.unitcode | 194,63,25,0 | |
| cristin.unitname | Institutt for teknisk kybernetikk | |
| cristin.ispublished | true | |
| cristin.fulltext | postprint | |
| cristin.qualitycode | 1 |
