Unsupervised learning of nanoindentation data to infer microstructural details of complex materials

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen Zhang, Clémence Bos, Stefan Sandfeld, Ruth Schwaiger
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Materials
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmats.2024.1440608/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846141533960536064
author Chen Zhang
Clémence Bos
Stefan Sandfeld
Stefan Sandfeld
Ruth Schwaiger
Ruth Schwaiger
author_facet Chen Zhang
Clémence Bos
Stefan Sandfeld
Stefan Sandfeld
Ruth Schwaiger
Ruth Schwaiger
author_sort Chen Zhang
collection DOAJ
description 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.
format Article
id doaj-art-9bc6ac921a0443c8b503b3467fa63c18
institution Kabale University
issn 2296-8016
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Materials
spelling doaj-art-9bc6ac921a0443c8b503b3467fa63c182024-12-04T06:46:10ZengFrontiers Media S.A.Frontiers in Materials2296-80162024-12-011110.3389/fmats.2024.14406081440608Unsupervised learning of nanoindentation data to infer microstructural details of complex materialsChen Zhang0Clémence Bos1Stefan Sandfeld2Stefan Sandfeld3Ruth Schwaiger4Ruth Schwaiger5Institute for Advanced Simulation – Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich GmbH, Jülich, GermanyInstitute for Applied Materials, Karlsruhe Institute of Technology (KIT), Karlsruhe, GermanyInstitute for Advanced Simulation – Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich GmbH, Jülich, GermanyChair of Materials Data Science and Informatics, Faculty of Georesources and Materials Engineering, RWTH Aachen University, Aachen, GermanyInstitute of Energy and Climate Research – Structure and Function of Materials (IEK-2), Forschungszentrum Jülich GmbH, Jülich, GermanyChair of Energy Engineering Materials, Faculty of Georesources and Materials Engineering, RWTH Aachen University, Aachen, GermanyIn 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.https://www.frontiersin.org/articles/10.3389/fmats.2024.1440608/fullunsupervised learningcross-validationGaussian mixture modelCu-Cr compositemechanical propertiesnanoindentation
spellingShingle Chen Zhang
Clémence Bos
Stefan Sandfeld
Stefan Sandfeld
Ruth Schwaiger
Ruth Schwaiger
Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
Frontiers in Materials
unsupervised learning
cross-validation
Gaussian mixture model
Cu-Cr composite
mechanical properties
nanoindentation
title Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
title_full Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
title_fullStr Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
title_full_unstemmed Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
title_short Unsupervised learning of nanoindentation data to infer microstructural details of complex materials
title_sort unsupervised learning of nanoindentation data to infer microstructural details of complex materials
topic unsupervised learning
cross-validation
Gaussian mixture model
Cu-Cr composite
mechanical properties
nanoindentation
url https://www.frontiersin.org/articles/10.3389/fmats.2024.1440608/full
work_keys_str_mv AT chenzhang unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials
AT clemencebos unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials
AT stefansandfeld unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials
AT stefansandfeld unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials
AT ruthschwaiger unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials
AT ruthschwaiger unsupervisedlearningofnanoindentationdatatoinfermicrostructuraldetailsofcomplexmaterials