dc.contributor.author | Celledoni, Elena | |
dc.contributor.author | Gustad, Halvor Snersrud | |
dc.contributor.author | Kopylov, Nikita | |
dc.contributor.author | Sundklakk, Henrik Sperre | |
dc.date.accessioned | 2020-06-30T08:37:37Z | |
dc.date.available | 2020-06-30T08:37:37Z | |
dc.date.created | 2020-01-08T22:02:20Z | |
dc.date.issued | 2019 | |
dc.identifier.issn | 0302-9743 | |
dc.identifier.uri | https://hdl.handle.net/11250/2659999 | |
dc.description.abstract | We investigate the possibility of predicting the bending moment of slender structures based on a limited number of deflection measurements. These predictions can help to estimate the wear and tear of the structures. We compare linear regression and a recurrent neural network on numerically simulated Euler–Bernoulli beam and drilling riser. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Springer | en_US |
dc.title | Predicting bending moments with machine learning | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.source.journal | Lecture Notes in Computer Science (LNCS) | en_US |
dc.identifier.doi | 10.1007/978-3-030-26980-7_19 | |
dc.identifier.cristin | 1768920 | |
dc.relation.project | EC/H2020/CHiPS | en_US |
dc.relation.project | Norges forskningsråd: 231632 | en_US |
dc.description.localcode | This article will not be available due to copyright restrictions (c) 2019 by Springer | en_US |
cristin.unitcode | 194,63,15,0 | |
cristin.unitname | Institutt for matematiske fag | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |