Optimizing artificial neural networks for mechanical problems by physics-based Rao-Blackwellization: example of a hyperelastic microsphere model

Simple item page
dc.contributor.authorGeuken, Gian-Luca
dc.contributor.authorMosler, Jörn
dc.contributor.authorKurzeja, Patrick
dc.date.accessioned2023-12-19T07:34:11Z
dc.date.available2023-12-19T07:34:11Z
dc.date.issued2023-03-24
dc.description.abstractThe Rao-Blackwell scheme provides an algorithm on how to implement sufficient information into statistical models and is adopted here to deterministic material modeling. Even crude initial predictions are improved significantly by Rao-Blackwellization, which is proven by an error inequality. This is first illustrated by an analytical example of hyperelasticity utilizing knowledge on principal stretches. Rao-Blackwellization improves a 1-d uniaxial strain-energy relation into a 3-d relation that resembles the classical micro-sphere approach. The presented scheme is moreover ideal for data-based approaches, because it supplements existing predictions with additional physical information. A second example hence illustrates the application of Rao-Blackwellization to an artificial neural network to improve its prediction on load paths, which were absent in the original training process.en
dc.identifier.urihttp://hdl.handle.net/2003/42237
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-24072
dc.language.isoende
dc.relation.ispartofseriesProceedings in applied mathematics and mechanics;22(1)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de
dc.subject.ddc620
dc.subject.ddc670
dc.subject.rswkStatistische Mechanikde
dc.subject.rswkNeuronales Netzde
dc.subject.rswkMaterialmodellierungde
dc.subject.rswkStatistikde
dc.subject.rswkHyperelastizitätde
dc.subject.rswkWerkstoffprüfungde
dc.titleOptimizing artificial neural networks for mechanical problems by physics-based Rao-Blackwellization: example of a hyperelastic microsphere modelen
dc.typeTextde
dc.type.publicationtypeArticlede
dcterms.accessRightsopen access
eldorado.secondarypublicationtruede
eldorado.secondarypublication.primarycitationGeuken, G., Mosler, J. and Kurzeja, P. (2023), Optimizing artificial neural networks for mechanical problems by physics-based Rao-Blackwellization: Example of a hyperelastic microsphere model. Proc. Appl. Math. Mech., 22: e202200325. https://doi.org/10.1002/pamm.202200325de
eldorado.secondarypublication.primaryidentifierDOI https://doi.org/10.1002/pamm.202200325de

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Proc Appl Math and Mech - 2023 - Geuken - Optimizing artificial neural networks for mechanical problems by physics‐based.pdf
Size:
325.41 KB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.85 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Institut für Mechanik