A latent space approach to multi-material topology optimization.
Saved in:
| Title: | A latent space approach to multi-material topology optimization. |
|---|---|
| Authors: | Sridhara, Saketh1 (AUTHOR), Deodhare, Gaurav G.2 (AUTHOR), Suresh, Krishnan2 (AUTHOR) ksuresh@wisc.edu |
| Source: | Structural & Multidisciplinary Optimization. Mar2026, Vol. 69 Issue 3, p1-17. 17p. |
| Subjects: | Latent variables, Optimizers (Computer software), Asymptotes, Design techniques, Simulation software |
| Abstract: | This work presents a novel approach for designing multi-alloy structures by simultaneously optimizing the material and topology. The proposed computational framework employs a material latent space integrated with density-based topology optimization in a two-step process. In the first step, a variational autoencoder (VAE), a type of neural network, maps a database of materials and their properties to a continuous, low-dimensional latent space. In the second step, the latent space is coupled with topology design variables (pseudo-densities) to simultaneously optimize material and topology. A gradient-based optimizer, specifically the method of moving asymptotes (MMA), traverses the latent space to select the material while simultaneously optimizing the topology. Optionally, one can add a penalization term that will drive the latent points towards real materials from the dataset. The framework is illustrated through 2D and 3D numerical examples using up to 20 materials, involving more than a million degrees of freedom. [ABSTRACT FROM AUTHOR] |
| Copyright of Structural & Multidisciplinary Optimization is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 191694294 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A latent space approach to multi-material topology optimization. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Sridhara%2C+Saketh%22">Sridhara, Saketh</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Deodhare%2C+Gaurav+G%2E%22">Deodhare, Gaurav G.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Suresh%2C+Krishnan%22">Suresh, Krishnan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> ksuresh@wisc.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Structural+%26+Multidisciplinary+Optimization%22">Structural & Multidisciplinary Optimization</searchLink>. Mar2026, Vol. 69 Issue 3, p1-17. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Latent+variables%22">Latent variables</searchLink><br /><searchLink fieldCode="DE" term="%22Optimizers+%28Computer+software%29%22">Optimizers (Computer software)</searchLink><br /><searchLink fieldCode="DE" term="%22Asymptotes%22">Asymptotes</searchLink><br /><searchLink fieldCode="DE" term="%22Design+techniques%22">Design techniques</searchLink><br /><searchLink fieldCode="DE" term="%22Simulation+software%22">Simulation software</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This work presents a novel approach for designing multi-alloy structures by simultaneously optimizing the material and topology. The proposed computational framework employs a material latent space integrated with density-based topology optimization in a two-step process. In the first step, a variational autoencoder (VAE), a type of neural network, maps a database of materials and their properties to a continuous, low-dimensional latent space. In the second step, the latent space is coupled with topology design variables (pseudo-densities) to simultaneously optimize material and topology. A gradient-based optimizer, specifically the method of moving asymptotes (MMA), traverses the latent space to select the material while simultaneously optimizing the topology. Optionally, one can add a penalization term that will drive the latent points towards real materials from the dataset. The framework is illustrated through 2D and 3D numerical examples using up to 20 materials, involving more than a million degrees of freedom. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Structural & Multidisciplinary Optimization is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191694294 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00158-025-04225-2 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 1 Subjects: – SubjectFull: Latent variables Type: general – SubjectFull: Optimizers (Computer software) Type: general – SubjectFull: Asymptotes Type: general – SubjectFull: Design techniques Type: general – SubjectFull: Simulation software Type: general Titles: – TitleFull: A latent space approach to multi-material topology optimization. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Sridhara, Saketh – PersonEntity: Name: NameFull: Deodhare, Gaurav G. – PersonEntity: Name: NameFull: Suresh, Krishnan IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 1615147X Numbering: – Type: volume Value: 69 – Type: issue Value: 3 Titles: – TitleFull: Structural & Multidisciplinary Optimization Type: main |
| ResultId | 1 |
