Neural integration for constitutive equations using small data

TL;DR

This paper introduces Neural Integration for Constitutive Equations, a deep learning method capable of deriving accurate material models from limited, incomplete, and noisy data, addressing the challenge of data scarcity in experimental observations.

Contribution

The paper presents a novel deep learning algorithm that learns constitutive models from scarce and partial data by solving the initial value problem of material state evolution.

Findings

Accurately learns from incomplete and noisy data

Requires only simple experimental protocols

Demonstrates robustness and consistency in benchmarks

Abstract

Data-driven models based on deep learning algorithms intend to overcome the limitations of traditional constitutive modelling by directly learning from data. However, the need for extensive data that collate the full state of the material is hindered by traditional experimental observations, which typically provide only small data - sparse and partial material state observations. To address this issue, we develop a novel deep learning algorithm referred to as Neural Integration for Constitutive Equations to discover constitutive models at the material point level from scarce and incomplete observations. It builds upon the solution of the initial value problem describing the time evolution of the material state, unlike the majority of data-driven approaches for constitutive modelling that require large data of increments of state variables. Numerical benchmarks demonstrate that the method can learn accurate, consistent, and robust constitutive models from incomplete, sparse, and noisy data collecting simple conventional experimental protocols.