Predicting and explaining nonlinear material response using deep Physically Guided Neural Networks with Internal Variables

TL;DR

This paper introduces Physically Guided Neural Networks with Internal Variables (PGNNIV), a model-free AI approach that predicts and explains complex nonlinear material behaviors using force-displacement data, applicable across various material types.

Contribution

The work develops PGNNIV, a novel neural network framework that enforces physical constraints to discover constitutive laws without internal variable data, enhancing explainability and prediction accuracy.

Findings

PGNNIV accurately predicts internal and external variables under unseen loads.

The method effectively uncovers constitutive laws for diverse material behaviors.

PGNNIV operates without internal variable data, demonstrating broad applicability.

Abstract

Nonlinear materials are often difficult to model with classical state model theory because they have a complex and sometimes inaccurate physical and mathematical description or we simply do not know how to describe such materials in terms of relations between external and internal variables. In many disciplines, Neural Network methods have arisen as powerful tools to identify very complex and non-linear correlations. In this work, we use the very recently developed concept of Physically Guided Neural Networks with Internal Variables (PGNNIV) to discover constitutive laws using a model-free approach and training solely with measured force-displacement data. PGNNIVs make a particular use of the physics of the problem to enforce constraints on specific hidden layers and are able to make predictions without internal variable data. We demonstrate that PGNNIVs are capable of predicting both internal and external variables under unseen load scenarios, regardless of the nature of the material considered (linear, with hardening or softening behavior and hyperelastic), unravelling the constitutive law of the material hence explaining its nature altogether, placing the method in what is known as eXplainable Artificial Intelligence (XAI).