Work

Machine-learning-based virtual fields method: Application to anisotropic hyperelasticity

Year: 2024

Type: article

Abstract: Thanks to advances of techniques like digital image correlation (DIC), the virtual fields method (VFM) has become a common approach to identifyingmechanical parameters of materials when full-field displacement data are available. However, it is limited to a priori selected classical material models.Recently, machine learning and model discovery has become a promising alternative for non-parametric material identification. This paper proposesan approach using a machine learning framework (NN-EUCLID) combined with the VFM. This framework has already demonstrated its good performancefor hyperelasticity using 2D simulated displacement fields and a loss function formulated with the local equilibrium gap. Our study focuses ontraining a similar NN-EUCLID framework with 3D displacement fields obtained in a bulge inflation test to discover mechanical models of arteries.Instead of using the local equilibrium gap, we employ the VFM to formulate loss functions. This novelty allows us to address issues such as unknownboundary conditions. We present numerical examples showcasing the ability to train hyperelastic models for isotropic and anisotropic materials. Resultsobtained with experimental data demonstrate the method’s effectiveness in training neural-network constitutive models for biological tissues using accessiblefull-field measurements.

Source: Computer Methods in Applied Mechanics and Engineering

DOI: 10.1016/j.cma.2024.117580

Authors: Shuangshuang Meng, Ali Akbar Karkhaneh Yousefi, Stéphane Avril

Institutions: Inserm, Mines Saint-Étienne, SAnté INgenierie BIOlogie Saint-Etienne, Université Jean Monnet, Université Jean Monnet

Language: English

Topic: Elasticity and Material Modeling

Subfield: Biomedical Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,660

Funder: Agence Nationale de la Recherche