Data analytics approach to predict the hardness of copper matrix composites

Authors

  • Somesh Kr. Bhattacharya Research Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, Japan
  • Ryoji Sahara Research Center for Structural Materials, National Institute for Materials Science, 1-2-1 Sengen, Tsukuba, Ibaraki 305-0047, Japan
  • Dušan Božić Department of Materials, „VINČA" Institute of Nuclear Sciences - National Institute of the Republic of Serbia, University of Belgrade, PO Box 522, 11001 Belgrade, Serbia
  • Jovana Ruzic Vinča Institute of Nuclear Sciences, University of Belgrade, PO Box 522, 11001 Belgrade

DOI:

https://doi.org/10.30544/567

Keywords:

Copper Matrix Composites, Hardness, Machine Learning, Regression Model

Abstract

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 (Ï, 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.

References

K. U. Kainer, Metal matrix composites custom-made materials for automotive and aerospace engineering, WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim, 2006

Crossreff

S. R. Pogson, P. Fox, C. Sutclisse, W. O'Neill: PRB 9 (2003) 334343.

Crossreff

M. Li, S. J. Zinkle, Comprehensive nuclear materials 4 (2012) 667-690.

Crossreff

Y. Zhan, Y. Z. J. Zeng: Tribol Lett 20 (2005) 163170.

Crossreff

M. Sobhani, A. Mirhabibi, H. Arabi, R. M. D. Brydson: Mater Sci Eng A 577 (2013) 1622.

Crossreff

W. S. Miller, F. J. Humphreys: Scripta Metallurgica et, 25 (1991) 33-38.

Crossreff

C. Zou, Z. Chen, E. Guo, H. Kang, G. Fan, W. Wang: RSC Adv, 8 (2018) 30777-30782.

Crossreff

S. J. Dong, Y. Zhou, Y. Shi, B. Chang: Metall Mater Trans A, 33(4) (2002) 1275-1280.

Crossreff

J. R. Groza, J. C. Gibeling: Mat Sci Eng A-Struct, 171 (1-2) (1993) 115-125.

Crossreff

H. Kimura, N.Muramatsu, K.Suzuki, Copper alloy and copper alloy manufacturing method, Patent Application Publication, US 0211346A1, United States.

X. Fan, X. Huang, Q. Liu, H. Ding, H. Wang, C. Hao: Results Phys, 14 (2019) 102494, 1-6.

Crossreff

J. Ruzic, J. Stasic, S. Markovic, K. Raic, D. Bozic: Sci Sinter, 46 (2) (2014) 217-224.

Crossreff

D. Xue, D. Xue, R. Yuan, Y. Zhou, P. V. Balachandran, X. Ding, J. Sun, T. Lookman: Acta Materialia 125 (2017) 532 - 541.

Crossreff

D. Shin, Y. Yamamoto, M. Brady, S. Lee, J. Haynes, Modern data analytics approach to predict creep of high temperature alloys, Acta Mater, 168 (2019) 321-330.

Crossreff

J. Wei, X. Chu, X.-Y. Sun, K. Xu, H.-X. Deng, J. Chen, Z. Wei, M. Lei: InfoMat 1 (3) (2019) 338-358.

Crossreff

J. Schmidt, M. R. G. Marques, S. Botti, M. A. L. Marques: NPJ Comput Mater, 5 (2019) 83, 1-36.

Crossreff

J. Ruzic, J. Stasic, V. Rajkovic, D. Bozic: Mater and Des, 62 (2014) 409-415.

Crossreff

J. Ruzic, J. Stasic, V. Rajkovic, K. Raic, D. Bozic: Sci Eng Compos Mater, 22 (2015) 665-671.

Crossreff

M. R. Segal, UCSF: Center for Bioinformatics and Molecular Biostatistics, (2004) 1-14.

L. Mason, J. Baxter, P. Bartlett, M. Frean: Advances in neural information processing systems, MIT Press. 12 (1999) 512-518.

Link

H. Drucker, C. C. Burges, L. Kaufman, A. J. Smola, V. N. Vapnik: Advances in neural information processing systems, NIPS, MIT-Press, 9 (1997) 155-161.

Link

V. Cherkassky, Y. Ma: Neural Comput, 15 (2003) 1691-1714.

Crossreff

J. Neter, M. H. Kutner, C. J. Nachtsheim, W. Wasserman, Applied linear statistical models, 4 Edition, Chicago: Irwin, 1996

Y. Zhang, J. Duchi, M. Wainwright: J Mach Learn Res, 16 (2015) 3299-3340.

Link

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, G. Louppe, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perror, E. Duchesnay: J Mach Learn Res, 12 (2012) 2825-2830.

Link

C. Sammut, G. I. Webb, Leave-one-out cross-validation in encyclopedia of machine learning, Springer, Boston, MA, 2010.

Crossreff

J. L. Devore, Probability and statistics for engineering and the sciences (8th ed.), Boston, MA: Cengage Learning (2011) 508-510.

Downloads

Published

2020-11-12

How to Cite

Bhattacharya, Somesh Kr., Ryoji Sahara, Dušan Božić, and Jovana Ruzic. 2020. “Data Analytics Approach to Predict the Hardness of Copper Matrix Composites”. Metallurgical and Materials Engineering 26 (4):357-64. https://doi.org/10.30544/567.

Issue

Section

Milan Jovanović - Memorial Issue