DC FieldValueLanguage
dc.contributor.authorKellner, Leon-
dc.contributor.authorStender, Merten-
dc.contributor.authorvon Bock und Polach, Rüdiger Ulrich Franz-
dc.contributor.authorEhlers, Sören-
dc.date.accessioned2022-05-30T08:44:11Z-
dc.date.available2022-05-30T08:44:11Z-
dc.date.issued2022-07-01-
dc.identifier.citationOcean Engineering 255: 111396 (2022-07-01)de_DE
dc.identifier.issn0029-8018de_DE
dc.identifier.urihttp://hdl.handle.net/11420/12735-
dc.description.abstractBuilding and using ice-related models is challenging due to the complexity of the material. A common issue, shared by both material models and (semi-)empirical approaches, is estimating unknown input parameters such as compressive strength. This is often done with additional empirical formulas which have drawbacks, e.g., they are based on a limited amount of data. Regarding material modeling, a strongly related problem is the prioritization of effects to include in the model. This is mostly done based on a subjective mix of knowledge, model purpose, and experimental studies limited to that purpose, which risks overlooking effects or interaction of effects, and limits transferability of material models to other scenarios. To tackle these issues, a hybrid approach of domain knowledge and explainable machine learning was used. A large ice test database was compiled to train machine learning models to predict compressive strength and behavior type. The machine learning models’ predictions were more accurate than existing empirical or analytical approaches and can thus be used as an alternative, though less straightforward, tool for such predictions. Further, the SHAP explainable AI method was applied to the predictions. Impact rankings of experimental parameters and interaction effects between parameters were analyzed and discussed in terms of ice mechanics. Top features were strain rate, triaxial stress state, temperature, and loading direction, but impact rankings were highly dependent on prediction target and type of ice. Few interaction effects were found. The approach adds objectivity to the prioritization of effects for material modeling and generated further insights into ice mechanics. It is also considered useful for other natural materials or generally when there is more data than knowledge.en
dc.language.isoende_DE
dc.relation.ispartofOcean engineeringde_DE
dc.subjectBrittlede_DE
dc.subjectDuctilede_DE
dc.subjectExplainable AIde_DE
dc.subjectIce compressive strengthde_DE
dc.subjectIce mechanicsde_DE
dc.subjectMachine learningde_DE
dc.subjectMaterial modelingde_DE
dc.titlePredicting compressive strength and behavior of ice and analyzing feature importance with explainable machine learning modelsde_DE
dc.typeArticlede_DE
dc.type.diniarticle-
dcterms.DCMITypeText-
tuhh.abstract.englishBuilding and using ice-related models is challenging due to the complexity of the material. A common issue, shared by both material models and (semi-)empirical approaches, is estimating unknown input parameters such as compressive strength. This is often done with additional empirical formulas which have drawbacks, e.g., they are based on a limited amount of data. Regarding material modeling, a strongly related problem is the prioritization of effects to include in the model. This is mostly done based on a subjective mix of knowledge, model purpose, and experimental studies limited to that purpose, which risks overlooking effects or interaction of effects, and limits transferability of material models to other scenarios. To tackle these issues, a hybrid approach of domain knowledge and explainable machine learning was used. A large ice test database was compiled to train machine learning models to predict compressive strength and behavior type. The machine learning models’ predictions were more accurate than existing empirical or analytical approaches and can thus be used as an alternative, though less straightforward, tool for such predictions. Further, the SHAP explainable AI method was applied to the predictions. Impact rankings of experimental parameters and interaction effects between parameters were analyzed and discussed in terms of ice mechanics. Top features were strain rate, triaxial stress state, temperature, and loading direction, but impact rankings were highly dependent on prediction target and type of ice. Few interaction effects were found. The approach adds objectivity to the prioritization of effects for material modeling and generated further insights into ice mechanics. It is also considered useful for other natural materials or generally when there is more data than knowledge.de_DE
tuhh.publisher.doi10.1016/j.oceaneng.2022.111396-
tuhh.publication.instituteKonstruktion und Festigkeit von Schiffen M-10de_DE
tuhh.publication.instituteStrukturdynamik M-14de_DE
tuhh.type.opus(wissenschaftlicher) Artikel-
dc.type.driverarticle-
dc.type.casraiJournal Article-
tuhh.container.volume255de_DE
dc.relation.projectEntwicklung und Simulation eines Mehrskalen-Materialmodells für das spröde Verhalten von Eis bei Struktur-Interaktionde_DE
dc.relation.projectWege zur Steigerung der Energiedissipation und Dämpfung in selbsterregten Strukturen mit irregulären Schwingungsantworten - Kombination datenbasierter Verfahren mit modellbasierten Zugängende_DE
dc.identifier.scopus2-s2.0-85129763506de_DE
tuhh.container.articlenumber111396de_DE
datacite.resourceTypeArticle-
datacite.resourceTypeGeneralJournalArticle-
item.grantfulltextnone-
item.creatorGNDKellner, Leon-
item.creatorGNDStender, Merten-
item.creatorGNDvon Bock und Polach, Rüdiger Ulrich Franz-
item.creatorGNDEhlers, Sören-
item.languageiso639-1en-
item.fulltextNo Fulltext-
item.openairetypeArticle-
item.mappedtypeArticle-
item.creatorOrcidKellner, Leon-
item.creatorOrcidStender, Merten-
item.creatorOrcidvon Bock und Polach, Rüdiger Ulrich Franz-
item.creatorOrcidEhlers, Sören-
item.cerifentitytypePublications-
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
crisitem.project.funderDeutsche Forschungsgemeinschaft (DFG)-
crisitem.project.funderDeutsche Forschungsgemeinschaft (DFG)-
crisitem.project.funderid501100001659-
crisitem.project.funderid501100001659-
crisitem.project.funderrorid018mejw64-
crisitem.project.funderrorid018mejw64-
crisitem.project.grantnoEH 485/11-1-
crisitem.project.grantnoHO 3852/12-2-
crisitem.author.deptKonstruktion und Festigkeit von Schiffen M-10-
crisitem.author.deptStrukturdynamik M-14-
crisitem.author.deptKonstruktion und Festigkeit von Schiffen M-10-
crisitem.author.deptKonstruktion und Festigkeit von Schiffen M-10-
crisitem.author.orcid0000-0001-9722-7508-
crisitem.author.orcid0000-0002-0888-8206-
crisitem.author.orcid0000-0002-4093-8381-
crisitem.author.orcid0000-0001-5698-9354-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
Appears in Collections:Publications without fulltext
Show simple item record

Page view(s)

26
Last Week
0
Last month
checked on Jun 7, 2023

Google ScholarTM

Check

Add Files to Item

Note about this record

Cite this record

Export

Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.