Support vector machines in reliability calculations of engineering structures

Simple item page
dc.contributor.authorSadílková Šomodíková, Martinacs
dc.contributor.authorLehký, Davidcs
dc.date.accessioned2025-10-14T12:24:17Z
dc.date.available2025-10-14T12:24:17Z
dc.date.issued2025-08-07cs
dc.description.abstractIn the paper, a metamodeling approach based on support vector regression is studied as a promising tool in the assessment of reliability level. The method consists of two steps: firstly, an approximation of the original limit state function is performed, and in the second step a failure probability or reliability index is calculated with a simpler, approximated function using traditional simulation techniques. Two problems with explicit limit state functions are used to study the effectivity of the method. In order to be as effective as possible with respect to computational effort, a stratified Latin Hypercube Sampling simulation method is utilized to properly select training set elements. The accuracy of the method is analyzed and compared with other surrogate modeling methods, namely the polynomial- and artificial neural network-based response surface method, achieving comparable results.en
dc.description.abstractIn the paper, a metamodeling approach based on support vector regression is studied as a promising tool in the assessment of reliability level. The method consists of two steps: firstly, an approximation of the original limit state function is performed, and in the second step a failure probability or reliability index is calculated with a simpler, approximated function using traditional simulation techniques. Two problems with explicit limit state functions are used to study the effectivity of the method. In order to be as effective as possible with respect to computational effort, a stratified Latin Hypercube Sampling simulation method is utilized to properly select training set elements. The accuracy of the method is analyzed and compared with other surrogate modeling methods, namely the polynomial- and artificial neural network-based response surface method, achieving comparable results.en
dc.description.embargo2026-08-07cs
dc.formattextcs
dc.format.extent1113-1118cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationEngineering Materials, Structures, Systems and Methods for a More Sustainable Future. 2025, p. 1113-1118.en
dc.identifier.doi10.1201/9781003677895-187cs
dc.identifier.isbn9781003677895cs
dc.identifier.orcid0000-0001-7117-4946cs
dc.identifier.orcid0000-0001-8176-4114cs
dc.identifier.other199005cs
dc.identifier.researcheridAAD-6219-2019cs
dc.identifier.researcheridAAK-9492-2020cs
dc.identifier.scopus56829580400cs
dc.identifier.scopus56389654700cs
dc.identifier.urihttps://hdl.handle.net/11012/255574
dc.language.isoencs
dc.publisherCRC Presscs
dc.relation.ispartofEngineering Materials, Structures, Systems and Methods for a More Sustainable Futurecs
dc.relation.urihttps://www.taylorfrancis.com/chapters/edit/10.1201/9781003677895-187/support-vector-machines-reliability-calculations-engineering-structures-šomodíková-lehkýcs
dc.rightsCreative Commons Attribution-NoDerivatives 4.0 Internationalcs
dc.rights.accessembargoedAccesscs
dc.rights.urihttp://creativecommons.org/licenses/by-nd/4.0/cs
dc.subjectSupport vector machinesen
dc.subjectreliability analysisen
dc.subjectfailure probabilityen
dc.subjectreliability indexen
dc.subjectsurrogate modelen
dc.subjectSupport vector machines
dc.subjectreliability analysis
dc.subjectfailure probability
dc.subjectreliability index
dc.subjectsurrogate model
dc.titleSupport vector machines in reliability calculations of engineering structuresen
dc.title.alternativeSupport vector machines in reliability calculations of engineering structuresen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionacceptedVersionen
sync.item.dbidVAV-199005en
sync.item.dbtypeVAVen
sync.item.insts2025.10.14 14:24:17en
sync.item.modts2025.10.14 09:55:19en
thesis.grantorVysoké učení technické v Brně. Fakulta stavební. Ústav stavební mechanikycs
Files
Collections
Ústav stavební mechaniky