Segmenting mechanically heterogeneous domains via unsupervised learning

TL;DR

This paper explores the use of unsupervised machine learning techniques to identify heterogeneous regions in deformable materials, aiming to improve understanding of material heterogeneity without relying on strict boundary conditions.

Contribution

It introduces unsupervised learning methods for clustering heterogeneous regions in mechanical data, providing a foundation for future tailored approaches.

Findings

Unsupervised clustering effectively identifies heterogeneous regions.

Current methods have limitations in accuracy and generalizability.

Published data and code facilitate further research.

Abstract

From biological organs to soft robotics, highly deformable materials are essential components of natural and engineered systems. These highly deformable materials can have heterogeneous material properties, and can experience heterogeneous deformations with or without underlying material heterogeneity. Many recent works have established that computational modeling approaches are well suited for understanding and predicting the consequences of material heterogeneity and for interpreting observed heterogeneous strain fields. In particular, there has been significant work towards developing inverse analysis approaches that can convert observed kinematic quantities (e.g., displacement, strain) to material properties and mechanical state. Despite the success of these approaches, they are not necessarily generalizable and often rely on tight control and knowledge of boundary conditions. Here, we will build on the recent advances (and ubiquity) of machine learning approaches to explore alternative approaches to detect patterns in heterogeneous material properties and mechanical behavior. Specifically, we will explore unsupervised learning approaches to clustering and ensemble clutering to identify heterogeneous regions. Overall, we find that these approaches are effective, yet limited in their abilities. Through this initial exploration (where all data and code is published alongside this manuscript), we set the stage for future studies that more specifically adapt these methods to mechanical data.