EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Active learning for adaptive surrogate model improvement in high-dimensional problems

Yulin Guo, Paromita Nath, Sankaran Mahadevan iD, Paul Witherell

Structural and Multidisciplinary Optimization · 2024-07 · 67 (7)

DOI: 10.1007/s00158-024-03816-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structural and Multidisciplinary Optimization, online erschienen am 10.07.2024. Verfasst von Yulin Guo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, Vanderbilt University, Nashville, TN 37235 USA. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute of Standards and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates a novel approach to efficiently construct and improve surrogate models in problems with high-dimensional input and output. In this approach, the principal components and corresponding features of the high-dimensional output are first identified. For each feature, the active subspace technique is used to identify a corresponding low-dimensional subspace of the input domain; then a surrogate model is built for each feature in its corresponding active subspace. A low-dimensional adaptive learning strategy is proposed to identify training samples to improve the surrogate model. In contrast to existing adaptive learning methods that focus on a scalar output or a small number of outputs, this paper addresses adaptive learning with high-dimensional input and output, with a novel learning function that balances exploration and exploitation, i.e., considering unexplored regions and high-error regions, respectively. The adaptive learning is in terms of the active variables in the low-dimensional space, and the newly added training samples can be easily mapped back to the original space for running the expensive physics model. The proposed method is demonstrated for the numerical simulation of an additive manufacturing part, with a high-dimensional field output quantity of interest (residual stress) in the component that has spatial variability due to the stochastic nature of multiple input variables (including process variables and material properties). Various factors in the adaptive learning process are investigated, including the number of training samples, range and distribution of the adaptive training samples, contributions of various errors, and the importance of exploration versus exploitation in the learning function.

Schlagwörter

Stichwörter der Autor:innen

Active learningAdditive manufacturingHigh dimensionSurrogate model

Autor:innen und Institutionen

  • Department of Civil and Environmental Engineering, Vanderbilt University, Nashville, TN 37235 USA.
  • Department of Mechanical Engineering, Rowan University, Glassboro, NJ 08028 USA.
  • Engineering Laboratory, National Institute of Standards and Technology, Gaithersburg, MD 20899 USA.

ORCID-Profile: Sankaran Mahadevan

Förderung

  • National Institute of Standards and Technology

Zitieren

APA

Guo, Y., Nath, P., Mahadevan, S., & Witherell, P. (2024). Active learning for adaptive surrogate model improvement in high-dimensional problems. Structural and Multidisciplinary Optimization, 67(7). https://doi.org/10.1007/s00158-024-03816-9

Vancouver

Guo Y, Nath P, Mahadevan S, Witherell P. Active learning for adaptive surrogate model improvement in high-dimensional problems. Structural and Multidisciplinary Optimization. 2024;67(7). doi:10.1007/s00158-024-03816-9

BibTeX
@article{Guo2024,
  author = {Guo, Yulin and Nath, Paromita and Mahadevan, Sankaran and Witherell, Paul},
  title = {Active learning for adaptive surrogate model improvement in high-dimensional problems},
  journal = {Structural and Multidisciplinary Optimization},
  year = {2024},
  volume = {67},
  number = {7},
  doi = {10.1007/s00158-024-03816-9}
}
Kostenlos starten →