Autoencoder-based non-intrusive model order reduction in continuum mechanics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kehls, Jannick, Kuhl, Ellen, Brepols, Tim, Linka, Kevin, Holthusen, Hagen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918134290579456
author Kehls, Jannick
Kuhl, Ellen
Brepols, Tim
Linka, Kevin
Holthusen, Hagen
author_facet Kehls, Jannick
Kuhl, Ellen
Brepols, Tim
Linka, Kevin
Holthusen, Hagen
contents We propose a non-intrusive, Autoencoder-based framework for reduced-order modeling in continuum mechanics. Our method integrates three stages: (i) an unsupervised Autoencoder compresses high-dimensional finite element solutions into a compact latent space, (ii) a supervised regression network maps problem parameters to latent codes, and (iii) an end-to-end surrogate reconstructs full-field solutions directly from input parameters. To overcome limitations of existing approaches, we propose two key extensions: a force-augmented variant that jointly predicts displacement fields and reaction forces at Neumann boundaries, and a multi-field architecture that enables coupled field predictions, such as in thermo-mechanical systems. The framework is validated on nonlinear benchmark problems involving heterogeneous composites, anisotropic elasticity with geometric variation, and thermo-mechanical coupling. Across all cases, it achieves accurate reconstructions of high-fidelity solutions while remaining fully non-intrusive. These results highlight the potential of combining deep learning with dimensionality reduction to build efficient and extensible surrogate models. Our publicly available implementation provides a foundation for integrating data-driven model order reduction into uncertainty quantification, optimization, and digital twin applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Autoencoder-based non-intrusive model order reduction in continuum mechanics
Kehls, Jannick
Kuhl, Ellen
Brepols, Tim
Linka, Kevin
Holthusen, Hagen
Computational Engineering, Finance, and Science
Artificial Intelligence
Machine Learning
We propose a non-intrusive, Autoencoder-based framework for reduced-order modeling in continuum mechanics. Our method integrates three stages: (i) an unsupervised Autoencoder compresses high-dimensional finite element solutions into a compact latent space, (ii) a supervised regression network maps problem parameters to latent codes, and (iii) an end-to-end surrogate reconstructs full-field solutions directly from input parameters. To overcome limitations of existing approaches, we propose two key extensions: a force-augmented variant that jointly predicts displacement fields and reaction forces at Neumann boundaries, and a multi-field architecture that enables coupled field predictions, such as in thermo-mechanical systems. The framework is validated on nonlinear benchmark problems involving heterogeneous composites, anisotropic elasticity with geometric variation, and thermo-mechanical coupling. Across all cases, it achieves accurate reconstructions of high-fidelity solutions while remaining fully non-intrusive. These results highlight the potential of combining deep learning with dimensionality reduction to build efficient and extensible surrogate models. Our publicly available implementation provides a foundation for integrating data-driven model order reduction into uncertainty quantification, optimization, and digital twin applications.
title Autoencoder-based non-intrusive model order reduction in continuum mechanics
topic Computational Engineering, Finance, and Science
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.02237