Neural network-based surrogate model in postprocessing of topology optimized structures.
Saved in:
| Title: | Neural network-based surrogate model in postprocessing of topology optimized structures. |
|---|---|
| Authors: | Persia, Jude Thaddeus1 (AUTHOR), Sung, Myung Kyun1 (AUTHOR), Lee, Soobum1 (AUTHOR) sblee@umbc.edu, Burns, Devin E.2 (AUTHOR) |
| Source: | Neural Computing & Applications. May2025, Vol. 37 Issue 15, p8845-8867. 23p. |
| Subjects: | Database design, Civil engineering, Wind tunnels, Finite element method, Torque |
| Abstract: | This paper proposes a general method of creating an accurate neural network-based surrogate model for postprocessing a topologically optimized structure. When topology optimization results are converted into computer-aided design (CAD) files with smooth boundaries for manufacturability, finite element method (FEM) based stresses often do not agree with the topology optimized results due to changes of surface and mesh density. The conversion between topology optimization derived results and CAD files often requires postprocessing, an additional fine tuning of the geometry parameters to reconcile the change of the stress values. In this work, a feedforward, deep artificial neural network (DANN) is presented with varying architecture parameters that are found for each stress output of interest. This network is trained with the data based on a combination of Design of Experiments (DoE) models that have the geometry dimensions as inputs and stress readings under various loads as the outputs. A DANN-based surrogate model is constructed to enable fine tuning of all relevant stress performance metrics. This method of constructing an artificial network-based surrogate model minimizes the number of FEM computations required to generate an optimized, post-processed design. We present a case study of postprocessing a wind tunnel balance, a measurement device that yields the six force and moment components of a test aircraft. It needs to be designed considering multiple stress measures under combinations of the six loading conditions. Excellent performance of a neural network is presented in this paper in terms of accurate prediction of the highly nonlinear stresses under combinations of the six loads. Von Mises stress predictions are within 10% and axial force sensor stress predictions are within 2% for the final post-processed topology. The results support its usefulness for postprocessing of topology optimized structures. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computing & Applications 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 |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 184953545 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Neural network-based surrogate model in postprocessing of topology optimized structures. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Persia%2C+Jude+Thaddeus%22">Persia, Jude Thaddeus</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sung%2C+Myung+Kyun%22">Sung, Myung Kyun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lee%2C+Soobum%22">Lee, Soobum</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> sblee@umbc.edu</i><br /><searchLink fieldCode="AR" term="%22Burns%2C+Devin+E%2E%22">Burns, Devin E.</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. May2025, Vol. 37 Issue 15, p8845-8867. 23p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Database+design%22">Database design</searchLink><br /><searchLink fieldCode="DE" term="%22Civil+engineering%22">Civil engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Wind+tunnels%22">Wind tunnels</searchLink><br /><searchLink fieldCode="DE" term="%22Finite+element+method%22">Finite element method</searchLink><br /><searchLink fieldCode="DE" term="%22Torque%22">Torque</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This paper proposes a general method of creating an accurate neural network-based surrogate model for postprocessing a topologically optimized structure. When topology optimization results are converted into computer-aided design (CAD) files with smooth boundaries for manufacturability, finite element method (FEM) based stresses often do not agree with the topology optimized results due to changes of surface and mesh density. The conversion between topology optimization derived results and CAD files often requires postprocessing, an additional fine tuning of the geometry parameters to reconcile the change of the stress values. In this work, a feedforward, deep artificial neural network (DANN) is presented with varying architecture parameters that are found for each stress output of interest. This network is trained with the data based on a combination of Design of Experiments (DoE) models that have the geometry dimensions as inputs and stress readings under various loads as the outputs. A DANN-based surrogate model is constructed to enable fine tuning of all relevant stress performance metrics. This method of constructing an artificial network-based surrogate model minimizes the number of FEM computations required to generate an optimized, post-processed design. We present a case study of postprocessing a wind tunnel balance, a measurement device that yields the six force and moment components of a test aircraft. It needs to be designed considering multiple stress measures under combinations of the six loading conditions. Excellent performance of a neural network is presented in this paper in terms of accurate prediction of the highly nonlinear stresses under combinations of the six loads. Von Mises stress predictions are within 10% and axial force sensor stress predictions are within 2% for the final post-processed topology. The results support its usefulness for postprocessing of topology optimized structures. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Computing & Applications 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=184953545 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00521-025-11039-2 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 23 StartPage: 8845 Subjects: – SubjectFull: Database design Type: general – SubjectFull: Civil engineering Type: general – SubjectFull: Wind tunnels Type: general – SubjectFull: Finite element method Type: general – SubjectFull: Torque Type: general Titles: – TitleFull: Neural network-based surrogate model in postprocessing of topology optimized structures. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Persia, Jude Thaddeus – PersonEntity: Name: NameFull: Sung, Myung Kyun – PersonEntity: Name: NameFull: Lee, Soobum – PersonEntity: Name: NameFull: Burns, Devin E. IsPartOfRelationships: – BibEntity: Dates: – D: 21 M: 05 Text: May2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 09410643 Numbering: – Type: volume Value: 37 – Type: issue Value: 15 Titles: – TitleFull: Neural Computing & Applications Type: main |
| ResultId | 1 |
