EUVIMEDEUVIMED entdecken
Crossref

FastSVD-ML–ROM: A reduced-order modeling framework based on machine learning for real-time applications

G.I. Drakoulas, T.V. Gortsas, G.C. Bourantas, V.N. Burganos, D. Polyzos

Computer Methods in Applied Mechanics and Engineering · 2023-09 · 414 · 116155

DOI: 10.1016/j.cma.2023.116155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods in Applied Mechanics and Engineering, 2023-09. Verfasst von G.I. Drakoulas und 4 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 96 Literaturangaben. Gefördert von: Karlsruhe Institute of Technology, DAAD.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital twins have emerged as a key technology for optimizing the performance of engineering products and systems. High-fidelity numerical simulations constitute the backbone of engineering design, providing an accurate insight into the performance of complex systems. However, large-scale, dynamic, non-linear models require significant computational resources and are prohibitive for real-time digital twin applications. To this end, reduced order models (ROMs) are employed, to approximate the high-fidelity solutions while accurately capturing the dominant aspects of the physical behavior. The present work proposes a new machine learning (ML) platform for the development of ROMs, to handle large-scale numerical problems dealing with transient nonlinear partial differential equations. Our framework, mentioned as $\textit{FastSVD-ML-ROM}$, utilizes $\textit{(i)}$ a singular value decomposition (SVD) update methodology, to compute a linear subspace of the multi-fidelity solutions during the simulation process, $\textit{(ii)}$ convolutional autoencoders for nonlinear dimensionality reduction, $\textit{(iii)}$ feed-forward neural networks to map the input parameters to the latent spaces, and $\textit{(iv)}$ long short-term memory networks to predict and forecast the dynamics of parametric solutions. The efficiency of the $\textit{FastSVD-ML-ROM}$ framework is demonstrated for a 2D linear convection-diffusion equation, the problem of fluid around a cylinder, and the 3D blood flow inside an arterial segment. The accuracy of the reconstructed results demonstrates the robustness and assesses the efficiency of the proposed approach.

Förderung

  • Karlsruhe Institute of Technology
  • DAAD

Zitieren

APA

Drakoulas, G., Gortsas, T., Bourantas, G., Burganos, V., & Polyzos, D. (2023). FastSVD-ML–ROM: A reduced-order modeling framework based on machine learning for real-time applications. Computer Methods in Applied Mechanics and Engineering, 414, 116155. https://doi.org/10.1016/j.cma.2023.116155

Vancouver

Drakoulas G, Gortsas T, Bourantas G, Burganos V, Polyzos D. FastSVD-ML–ROM: A reduced-order modeling framework based on machine learning for real-time applications. Computer Methods in Applied Mechanics and Engineering. 2023;414:116155. doi:10.1016/j.cma.2023.116155

BibTeX
@article{Drakoulas2023,
  author = {Drakoulas, G.I. and Gortsas, T.V. and Bourantas, G.C. and Burganos, V.N. and Polyzos, D.},
  title = {FastSVD-ML–ROM: A reduced-order modeling framework based on machine learning for real-time applications},
  journal = {Computer Methods in Applied Mechanics and Engineering},
  year = {2023},
  volume = {414},
  pages = {116155},
  doi = {10.1016/j.cma.2023.116155}
}
Kostenlos starten →