Academic Journal
TwinLab: a framework for data-efficient training of non-intrusive reduced-order models for digital twins.
| Τίτλος: | TwinLab: a framework for data-efficient training of non-intrusive reduced-order models for digital twins. |
|---|---|
| Συγγραφείς: | Kannapinn, Maximilian, Schäfer, Michael, Weeger, Oliver |
| Πηγή: | Engineering Computations; 2025, Vol. 42 Issue 7, p2406-2426, 21p |
| Θεματικοί όροι: | Digital twin, Reduced-order models, Simulation methods & models |
| Περίληψη: | Purpose: Simulation-based digital twins represent an effort to provide high-accuracy real-time insights into operational physical processes. However, the computation time of many multi-physical simulation models is far from real-time. It might even exceed sensible time frames to produce sufficient data for training data-driven reduced-order models. This study presents TwinLab, a framework for data-efficient, yet accurate training of neural-ODE type reduced-order models with only two data sets. Design/methodology/approach: Correlations between test errors of reduced-order models and distinct features of corresponding training data are investigated. Having found the single best data sets for training, a second data set is sought with the help of similarity and error measures to enrich the training process effectively. Findings: Adding a suitable second training data set in the training process reduces the test error by up to 49% compared to the best base reduced-order model trained only with one data set. Such a second training data set should at least yield a good reduced-order model on its own and exhibit higher levels of dissimilarity to the base training data set regarding the respective excitation signal. Moreover, the base reduced-order model should have elevated test errors on the second data set. The relative error of the time series ranges from 0.18% to 0.49%. Prediction speed-ups of up to a factor of 36,000 are observed. Originality/value: The proposed computational framework facilitates the automated, data-efficient extraction of non-intrusive reduced-order models for digital twins from existing simulation models, independent of the simulation software. [ABSTRACT FROM AUTHOR] |
| Copyright of Engineering Computations is the property of Emerald Publishing Limited 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.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Links: – Type: other Text: Availability: 0 CustomLinks: – Url: https://www.emerald.com/insight/content/doi/10.1108/EC-11-2023-0855 Name: Emerald Insight (All Content) (s7799221) Category: fullText Text: View full text at Emerald MouseOverText: View full text at Emerald |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 189519523 RelevancyScore: 1023 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1023.08752441406 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: TwinLab: a framework for data-efficient training of non-intrusive reduced-order models for digital twins. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kannapinn%2C+Maximilian%22">Kannapinn, Maximilian</searchLink><br /><searchLink fieldCode="AR" term="%22Schäfer%2C+Michael%22">Schäfer, Michael</searchLink><br /><searchLink fieldCode="AR" term="%22Weeger%2C+Oliver%22">Weeger, Oliver</searchLink> – Name: TitleSource Label: Source Group: Src Data: Engineering Computations; 2025, Vol. 42 Issue 7, p2406-2426, 21p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Digital+twin%22">Digital twin</searchLink><br /><searchLink fieldCode="DE" term="%22Reduced-order+models%22">Reduced-order models</searchLink><br /><searchLink fieldCode="DE" term="%22Simulation+methods+%26+models%22">Simulation methods & models</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Purpose: Simulation-based digital twins represent an effort to provide high-accuracy real-time insights into operational physical processes. However, the computation time of many multi-physical simulation models is far from real-time. It might even exceed sensible time frames to produce sufficient data for training data-driven reduced-order models. This study presents TwinLab, a framework for data-efficient, yet accurate training of neural-ODE type reduced-order models with only two data sets. Design/methodology/approach: Correlations between test errors of reduced-order models and distinct features of corresponding training data are investigated. Having found the single best data sets for training, a second data set is sought with the help of similarity and error measures to enrich the training process effectively. Findings: Adding a suitable second training data set in the training process reduces the test error by up to 49% compared to the best base reduced-order model trained only with one data set. Such a second training data set should at least yield a good reduced-order model on its own and exhibit higher levels of dissimilarity to the base training data set regarding the respective excitation signal. Moreover, the base reduced-order model should have elevated test errors on the second data set. The relative error of the time series ranges from 0.18% to 0.49%. Prediction speed-ups of up to a factor of 36,000 are observed. Originality/value: The proposed computational framework facilitates the automated, data-efficient extraction of non-intrusive reduced-order models for digital twins from existing simulation models, independent of the simulation software. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Engineering Computations is the property of Emerald Publishing Limited 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=edb&AN=189519523 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1108/EC-11-2023-0855 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 2406 Subjects: – SubjectFull: Digital twin Type: general – SubjectFull: Reduced-order models Type: general – SubjectFull: Simulation methods & models Type: general Titles: – TitleFull: TwinLab: a framework for data-efficient training of non-intrusive reduced-order models for digital twins. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kannapinn, Maximilian – PersonEntity: Name: NameFull: Schäfer, Michael – PersonEntity: Name: NameFull: Weeger, Oliver IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: 2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 02644401 Numbering: – Type: volume Value: 42 – Type: issue Value: 7 Titles: – TitleFull: Engineering Computations Type: main |
| ResultId | 1 |