Unsupervised Learning of Nanoindentation Data to Infer Microstructural Details of Complex Materials

TL;DR

This paper applies unsupervised Gaussian mixture models to analyze nanoindentation data of Cu-Cr composites, revealing microstructural phases and assessing data sufficiency for reliable property inference.

Contribution

It introduces an unsupervised learning approach combined with cross-validation to identify mechanical phases and determine data requirements in nanoindentation studies.

Findings

Identification of distinct mechanical phases in Cu-Cr composites

Method for assessing data sufficiency in nanoindentation analysis

Demonstration of Gaussian mixture models for microstructural inference

Abstract

In this study, Cu-Cr composites were studied by nanoindentation. Arrays of indents were placed over large areas of the samples resulting in datasets consisting of several hundred measurements of Young's modulus and hardness at varying indentation depths. The unsupervised learning technique, Gaussian mixture model, was employed to analyze the data, which helped to determine the number of "mechanical phases" and the respective mechanical properties. Additionally, a cross-validation approach was introduced to infer whether the data quantity was adequate and to suggest the amount of data required for reliable predictions -- one of the often encountered but difficult to resolve issues in machine learning of materials science problems.