Discovery of Hyperelastic Constitutive Laws from Experimental Data with EUCLID

TL;DR

This paper evaluates EUCLID, an automated framework for discovering hyperelastic constitutive laws from experimental data, demonstrating its effectiveness compared to traditional methods across various geometries and data types.

Contribution

The paper introduces and assesses EUCLID, a novel automated approach for constitutive law discovery that integrates model selection and parameter identification in a unified pipeline.

Findings

EUCLID achieves comparable or better predictive accuracy than traditional methods.

EUCLID effectively generalizes to unseen geometries and different datasets.

The framework quantifies experimental noise and explores material state space coverage.

Abstract

We assess the performance of EUCLID, Efficient Unsupervised Constitutive Law Identification and Discovery, a recently proposed framework for automated discovery of constitutive laws, on experimental data. Mechanical tests are performed on natural rubber specimens spanning simple to complex geometries, from which we collect both global, force elongation, and local, full-field displacement, measurements. Using these data, we obtain constitutive laws via two routes, the conventional identification of unknown parameters in a priori selected material models, and EUCLID, which automates model selection and parameter identification within a unified model-discovery pipeline. We compare the two methodologies using global versus local data, analyze predictive accuracy, and examine generalization to unseen geometries. Moreover, we quantify the experimental noise, investigate the coverage of the material state space achieved by each approach and discuss the relative performance of different datasets and different a priori chosen models versus EUCLID.