Mechanistic machine learning for metamaterial fatigue strength design from first principles in additive manufacturing

Simple item page
dc.contributor.authorAwd, Mustafa
dc.contributor.authorSaeed, Lobna
dc.contributor.authorMünstermann, Sebastian
dc.contributor.authorFaes, Matthias
dc.contributor.authorWalther, Frank
dc.date.accessioned2025-03-07T11:39:56Z
dc.date.available2025-03-07T11:39:56Z
dc.date.issued2024-04-08
dc.description.abstractDigital control in manufacturing processes produces significant amounts of metadata. The production process metadata, such as thermal and optical measurements, enables a higher degree of property grading than uninstrumented manufacturing and feedback for fault detection. This study explores how metadata can design fatigue-resistant structures using physically grounded models such as density functional theory, cyclic plasticity, and fracture mechanics that train machine learning algorithms. Machine learning models work very efficiently in their trained physical space. In comparison, mechanistic models are computationally costly for complex phenomena such as fatigue. We show how fatigue can be administered consistently at all scales by energy-based criteria and how a mechanistic function can be built based on this concept. The energy mechanistic function allows exact quantification of the effect of the existing flaws from manufacturing on fatigue lifetime under certain load boundary conditions. Since the mechanistic function is local and subscale to the prediction scale of the machine learning model, it can be used to build density functions for probabilistic regression of the fatigue property on the scale above. The analysis is applied to the selective laser melting process due to the availability of digital control and metadata generation during deposition.en
dc.identifier.urihttp://hdl.handle.net/2003/43521
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-25354
dc.language.isoen
dc.relation.ispartofseriesMaterials and design; 241
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectDensity functional theory (DFT)en
dc.subjectFunctional gradingen
dc.subjectMachine learning (ML)en
dc.subjectFatigue strengthen
dc.subjectCohesion energyen
dc.subjectAdditive manufacturing (AM)en
dc.subjectLifetime predictionen
dc.subjectBayesian statisticsen
dc.subjectProcess monitoringen
dc.subjectArtificial intelligence (AI)en
dc.subject.ddc660
dc.subject.rswkDichtefunktionalformalismusde
dc.subject.rswkFunktioneller Gradientenwerkstoffde
dc.subject.rswkMaschinelles Lernende
dc.subject.rswkDauerfestigkeitde
dc.subject.rswkKohäsionde
dc.subject.rswkHaltbarkeitde
dc.subject.rswkBayes-Entscheidungstheoriede
dc.subject.rswkProzessüberwachungde
dc.subject.rswkKünstliche Intelligenzde
dc.titleMechanistic machine learning for metamaterial fatigue strength design from first principles in additive manufacturingen
dc.typeText
dc.type.publicationtypeArticle
dcterms.accessRightsopen access
eldorado.secondarypublicationtrue
eldorado.secondarypublication.primarycitationMustafa Awd, Lobna Saeed, Sebastian Münstermann, Matthias Faes, Frank Walther. Mechanistic machine learning for metamaterial fatigue strength design from first principles in additive manufacturing. Materials & Design, Volume 241, 2024, 112889, https://doi.org/10.1016/j.matdes.2024.112889.
eldorado.secondarypublication.primaryidentifierhttps://doi.org/10.1016/j.matdes.2024.112889

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0264127524002624-main.pdf
Size:
5.77 MB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.82 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Lehrstuhl für Werkstoffprüftechnik