EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multiscale topology optimization using machine learning and displacement-driven microstructures

Joel C. Najmon, Andres Tovar

Structural and Multidisciplinary Optimization · 2025-09 · 68 (9)

DOI: 10.1007/s00158-025-04115-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structural and Multidisciplinary Optimization, online erschienen am 01.09.2025. Verfasst von Joel C. Najmon und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Naval Air Warfare Center, Aircraft Division.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multiscale topology optimization (MSTO) enables the design of hierarchical structures with enhanced performance and complexity. However, solving nested optimization problems at multiple scales imposes high computational costs. This paper introduces a machine learning-based MSTO (ML-MSTO) framework that leverages displacement-driven topology-optimized microstructures (TOMs). An artificial neural network is trained to predict homogenized stiffness tensors of TOMs based on macroscale densities and nodal displacements. This surrogate model enables efficient macroscale outer-loop optimization by avoiding microscale inner-loop optimization. Sensitivities are computed analytically from the neural network’s Jacobian, eliminating the need for finite differences. The method is demonstrated on 2D and 3D benchmark problems, generating high-fidelity, non-periodic multiscale structures with excellent compliance performance.

Förderung

  • National Science Foundation
  • Naval Air Warfare Center, Aircraft Division

Zitieren

APA

Najmon, J. C., & Tovar, A. (2025). Multiscale topology optimization using machine learning and displacement-driven microstructures. Structural and Multidisciplinary Optimization, 68(9). https://doi.org/10.1007/s00158-025-04115-7

Vancouver

Najmon JC, Tovar A. Multiscale topology optimization using machine learning and displacement-driven microstructures. Structural and Multidisciplinary Optimization. 2025;68(9). doi:10.1007/s00158-025-04115-7

BibTeX
@article{Najmon2025,
  author = {Najmon, Joel C. and Tovar, Andres},
  title = {Multiscale topology optimization using machine learning and displacement-driven microstructures},
  journal = {Structural and Multidisciplinary Optimization},
  year = {2025},
  volume = {68},
  number = {9},
  doi = {10.1007/s00158-025-04115-7}
}
Kostenlos starten →