Work

Autoencoder-based non-intrusive model order reduction for anisotropic and multi-physics problems

Year: 2026

Type: article

Abstract: 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.

Source: Computational Mechanics

DOI: 10.1007/s00466-026-02870-y

Authors: Jannick Kehls, Ellen Kuhl, Tim Brepols, Kevin Linka, Hagen Holthusen

Institutions: RWTH Aachen University, Stanford University, Friedrich-Alexander-Universität Erlangen-Nürnberg

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,990

Funders: National Science Foundation, Deutsche Forschungsgemeinschaft, Division of Civil, Mechanical and Manufacturing Innovation