Data analytics approach to predict the hardness of copper matrix composites
Copper matrix composite materials have exhibited a high potential in applications where excellent conductivity and mechanical properties are required. In this study, the machine learning models have been applied to predict the hardness of the copper matrix composite materials (CuMCs) produced via th...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The Netherlands Press
2020-11-01
|
Series: | Metallurgical & Materials Engineering |
Subjects: | |
Online Access: | https://metall-mater-eng.com/index.php/home/article/view/567 |
_version_ | 1797963286658940928 |
---|---|
author | Somesh Kr. Bhattacharya Ryoji Sahara Dušan Božić Jovana Ruzic |
author_facet | Somesh Kr. Bhattacharya Ryoji Sahara Dušan Božić Jovana Ruzic |
author_sort | Somesh Kr. Bhattacharya |
collection | DOAJ |
description | Copper matrix composite materials have exhibited a high potential in applications where excellent conductivity and mechanical properties are required. In this study, the machine learning models have been applied to predict the hardness of the copper matrix composite materials (CuMCs) produced via the powder metallurgy technique. Six different machine learning regression models were employed. The observed CuMCs were reinforced with two different volume fractions (2 vol.% and 7vol.%) of ZrB2 particles. Based on experimental work, we extracted the independent variables (features) like the milling time (MT, Hours), dislocation density (DD, m-2), average particle size (PS, μm), density (ρ, g/cm3), and yield stress (σ, MPa) while the Vickers hardness (MPa) was used as the dependent variable. Feature selection was performed by calculation the Pearson correlation coefficient (PCC) between the independent and dependent variables. The predictive accuracy higher than 80% was achieved for Cu-7vol.% ZrB2 and lower for the Cu-2vol.% ZrB2. |
first_indexed | 2024-04-11T01:26:02Z |
format | Article |
id | doaj.art-68809bbcb76c40258cefda11dbbc6a9b |
institution | Directory Open Access Journal |
issn | 2217-8961 |
language | English |
last_indexed | 2024-04-11T01:26:02Z |
publishDate | 2020-11-01 |
publisher | The Netherlands Press |
record_format | Article |
series | Metallurgical & Materials Engineering |
spelling | doaj.art-68809bbcb76c40258cefda11dbbc6a9b2023-01-03T10:16:21ZengThe Netherlands PressMetallurgical & Materials Engineering2217-89612020-11-0126435736410.30544/567567Data analytics approach to predict the hardness of copper matrix compositesSomesh Kr. Bhattacharya0Ryoji Sahara1Dušan Božić2Jovana Ruzic3Research Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, JapanResearch Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, JapanDepartment of Materials, „VINČA" Institute of Nuclear Sciences - National Institute of thе Republic of Serbia, University of Belgrade, PO Box 522, 11001 Belgrade, SerbiaVinča Institute of Nuclear Sciences, University of Belgrade, PO Box 522, 11001 BelgradeCopper matrix composite materials have exhibited a high potential in applications where excellent conductivity and mechanical properties are required. In this study, the machine learning models have been applied to predict the hardness of the copper matrix composite materials (CuMCs) produced via the powder metallurgy technique. Six different machine learning regression models were employed. The observed CuMCs were reinforced with two different volume fractions (2 vol.% and 7vol.%) of ZrB2 particles. Based on experimental work, we extracted the independent variables (features) like the milling time (MT, Hours), dislocation density (DD, m-2), average particle size (PS, μm), density (ρ, g/cm3), and yield stress (σ, MPa) while the Vickers hardness (MPa) was used as the dependent variable. Feature selection was performed by calculation the Pearson correlation coefficient (PCC) between the independent and dependent variables. The predictive accuracy higher than 80% was achieved for Cu-7vol.% ZrB2 and lower for the Cu-2vol.% ZrB2.https://metall-mater-eng.com/index.php/home/article/view/567copper matrix compositeshardnessmachine learningregression model |
spellingShingle | Somesh Kr. Bhattacharya Ryoji Sahara Dušan Božić Jovana Ruzic Data analytics approach to predict the hardness of copper matrix composites Metallurgical & Materials Engineering copper matrix composites hardness machine learning regression model |
title | Data analytics approach to predict the hardness of copper matrix composites |
title_full | Data analytics approach to predict the hardness of copper matrix composites |
title_fullStr | Data analytics approach to predict the hardness of copper matrix composites |
title_full_unstemmed | Data analytics approach to predict the hardness of copper matrix composites |
title_short | Data analytics approach to predict the hardness of copper matrix composites |
title_sort | data analytics approach to predict the hardness of copper matrix composites |
topic | copper matrix composites hardness machine learning regression model |
url | https://metall-mater-eng.com/index.php/home/article/view/567 |
work_keys_str_mv | AT someshkrbhattacharya dataanalyticsapproachtopredictthehardnessofcoppermatrixcomposites AT ryojisahara dataanalyticsapproachtopredictthehardnessofcoppermatrixcomposites AT dusanbozic dataanalyticsapproachtopredictthehardnessofcoppermatrixcomposites AT jovanaruzic dataanalyticsapproachtopredictthehardnessofcoppermatrixcomposites |