Academic Journal
View in EDS

Lightweight return-mapping surrogates for multiscale plasticity: a practical guide.

Bibliographic Details
Title: Lightweight return-mapping surrogates for multiscale plasticity: a practical guide.
Authors: Daneshyar, Alireza1 (AUTHOR) alireza.daneshyar@tum.de, Herrmann, Leon1 (AUTHOR), Kollmannsberger, Stefan1,2 (AUTHOR)
Source: Computational Mechanics. Aug2026, p1-27. 27p.
Subject Terms: *Material plasticity, *Artificial neural networks, *Finite element method, *Subroutines (Computer programs), *Computational mechanics
Abstract: This paper presents a practical guide to building lightweight neural-network surrogates for the plastic return-mapping process in concurrent multiscale (FE2) simulations. Rather than proposing a new architecture, we show how a deliberately simple feed-forward network, structured to mirror the classical return-mapping update, can replace the prohibitively expensive nested fine-scale solves that dominate the cost of conventional FE2 schemes based on FFT homogenization at the meso-scale. We walk through the full workflow: generating training data from incremental homogenization analyses, constructing a compact yet sufficient dataset, embedding material symmetries directly into the mapping, and deploying the trained network as a user-defined material subroutine (UMAT) in a standard finite-element solver—enabling widespread use. A sensitivity study examines the model’s robustness to data density, increment size, and mesh refinement, and we characterize the regimes in which the surrogate holds and where it breaks down. For the macroscopically isotropic, two-dimensional plane-stress setting considered here, the surrogate reproduces the reference response while reducing the per-analysis cost from hours to seconds with speed-ups up to 30,000 over standard FE2. Moreover, by eliminating the need to store and update the extensive microscale state variables, it drastically reduces memory requirements and enables substantially finer finite element discretizations that would otherwise be impossible. The approach extends naturally to three dimensions and to weaker symmetry assumptions, given an appropriate sampling strategy and dataset. [ABSTRACT FROM AUTHOR]
Database: Academic Search Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://dx.doi.org/doi:10.1007/s00466-026-02849-9
    Name: EDS - Springer Nature Journals (s7799221)
    Category: fullText
    Text: View record at Springer
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=01787675&ISBN=&volume=&issue=&date=20260831&spage=1&pages=1-27&title=Computational Mechanics&atitle=Lightweight%20return-mapping%20surrogates%20for%20multiscale%20plasticity%3A%20a%20practical%20guide.&aulast=Daneshyar%2C%20Alireza&id=DOI:10.1007/s00466-026-02849-9
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: asx
DbLabel: Academic Search Index
An: 196593820
RelevancyScore: 1452
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1452.42541503906
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Lightweight return-mapping surrogates for multiscale plasticity: a practical guide.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Daneshyar%2C+Alireza%22">Daneshyar, Alireza</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> alireza.daneshyar@tum.de</i><br /><searchLink fieldCode="AR" term="%22Herrmann%2C+Leon%22">Herrmann, Leon</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kollmannsberger%2C+Stefan%22">Kollmannsberger, Stefan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computational+Mechanics%22">Computational Mechanics</searchLink>. Aug2026, p1-27. 27p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Material+plasticity%22">Material plasticity</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Finite+element+method%22">Finite element method</searchLink><br />*<searchLink fieldCode="DE" term="%22Subroutines+%28Computer+programs%29%22">Subroutines (Computer programs)</searchLink><br />*<searchLink fieldCode="DE" term="%22Computational+mechanics%22">Computational mechanics</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper presents a practical guide to building lightweight neural-network surrogates for the plastic return-mapping process in concurrent multiscale (FE2) simulations. Rather than proposing a new architecture, we show how a deliberately simple feed-forward network, structured to mirror the classical return-mapping update, can replace the prohibitively expensive nested fine-scale solves that dominate the cost of conventional FE2 schemes based on FFT homogenization at the meso-scale. We walk through the full workflow: generating training data from incremental homogenization analyses, constructing a compact yet sufficient dataset, embedding material symmetries directly into the mapping, and deploying the trained network as a user-defined material subroutine (UMAT) in a standard finite-element solver—enabling widespread use. A sensitivity study examines the model’s robustness to data density, increment size, and mesh refinement, and we characterize the regimes in which the surrogate holds and where it breaks down. For the macroscopically isotropic, two-dimensional plane-stress setting considered here, the surrogate reproduces the reference response while reducing the per-analysis cost from hours to seconds with speed-ups up to 30,000 over standard FE2. Moreover, by eliminating the need to store and update the extensive microscale state variables, it drastically reduces memory requirements and enables substantially finer finite element discretizations that would otherwise be impossible. The approach extends naturally to three dimensions and to weaker symmetry assumptions, given an appropriate sampling strategy and dataset. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=196593820
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00466-026-02849-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 27
        StartPage: 1
    Subjects:
      – SubjectFull: Material plasticity
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Finite element method
        Type: general
      – SubjectFull: Subroutines (Computer programs)
        Type: general
      – SubjectFull: Computational mechanics
        Type: general
    Titles:
      – TitleFull: Lightweight return-mapping surrogates for multiscale plasticity: a practical guide.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Daneshyar, Alireza
      – PersonEntity:
          Name:
            NameFull: Herrmann, Leon
      – PersonEntity:
          Name:
            NameFull: Kollmannsberger, Stefan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 31
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01787675
          Titles:
            – TitleFull: Computational Mechanics
              Type: main
ResultId 1