Simulation of hyperelastic materials in real-time using Deep Learning

• Published in: arXiv.org
• Main Authors: Mendizabal, Andrea, Márquez-Neila, Pablo, Cotin, Stéphane
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 06.11.2019
• Subjects: Algorithms; Artificial neural networks; Cantilever beams; Computer Science - Computational Engineering, Finance, and Science; Computer Science - Learning; Computer simulation; Contact force; Deep learning; Domain decomposition methods; Finite element method; Machine learning; Mathematical models; Meshing; Model reduction; Nonlinear programming; Numerical methods; Physics - Computational Physics; Proper Orthogonal Decomposition
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.1904.06197

The finite element method (FEM) is among the most commonly used numerical methods for solving engineering problems. Due to its computational cost, various ideas have been introduced to reduce computation times, such as domain decomposition, parallel computing, adaptive meshing, and model order reduction. In this paper we present U-Mesh: a data-driven method based on a U-Net architecture that approximates the non-linear relation between a contact force and the displacement field computed by a FEM algorithm. We show that deep learning, one of the latest machine learning methods based on artificial neural networks, can enhance computational mechanics through its ability to encode highly non-linear models in a compact form. Our method is applied to two benchmark examples: a cantilever beam and an L-shape subject to moving punctual loads. A comparison between our method and proper orthogonal decomposition (POD) is done through the paper. The results show that U-Mesh can perform very fast simulations on various geometries, mesh resolutions and number of input forces with very small errors.