Abstract
The design of high entropy alloys (HEAs) can be accelerated using machine learning (ML) algorithms. In the current study, the design parameter’s effect on the algorithm prediction was established using Shapley additive explanation (SHAP) values. The higher dimension problem is reduced to lower dimension using kernel principal component analysis (KPCA). Testing accuracy of more than 85 pct was obtained for the support vector machine (SVM) with KPCA. Experimental data comparison confirms the improvement of accuracy for the decision tree (DT) and random forest (RF) after applying KPCA.
Notes
THERMO-CALC is a trademark of Thermo-Calc software
References
D.B. Miracle and O.N. Senkov: Acta Mater., 2017, vol. 122, pp. 448–511.
O.N. Senkov, J.D. Miller, D.B. Miracle, and C. Woodward: Nat. Commun., 2015, vol. 6, pp. 1–10.
H. Jiang, D. Qiao, Y. Lu, Z. Ren, Z. Cao, T. Wang, and T. Li: Scripta Mater., 2019, vol. 165, pp. 145–49.
N. Shah, M.R. Rahul, and G. Phanikumar: Metall. Mater. Trans. A, 2021, vol. 52A, pp. 1574–80.
Y.V. Krishna, U.K. Jaiswal, and M.R. Rahul: Scripta Mater., 2021, vol. 197, p. 113804.
J.M. Rickman, T. Lookman, and S.V. Kalinin: Acta Mater., 2019, vol. 168, pp. 473–510.
L. Ward and C. Wolverton: Curr. Opin. Solid State Mater. Sci., 2017, vol. 21, pp. 167–76.
R. Jose and S. Ramakrishna: Appl. Mater. Today, 2018, vol. 10, pp. 127–32.
J.M. Rickman, H.M. Chan, M.P. Harmer, J.A. Smeltzer, C.J. Marvel, A. Roy, and G. Balasubramanian: Nat. Commun., 2019, vol. 10, pp. 1–10.
A. Roy, T. Babuska, B. Krick, and G. Balasubramanian: Scripta Mater., 2020, vol. 185, pp. 152–58.
S. Yang, J. Lu, F. Xing, L. Zhang, and Y. Zhong: Acta Mater., 2020, vol. 192, pp. 11–19.
Q. Wu, Z. Wang, X. Hu, T. Zheng, Z. Yang, F. He, J. Li, and J. Wang: Acta Mater., 2020, vol. 182, pp. 278–86.
H. Jiang, K. Han, X. Gao, Y. Lu, Z. Cao, M.C. Gao, J.A. Hawk, and T. Li: Mater. Des., 2018, vol. 142, pp. 101–05.
F. He, Z. Wang, C. Ai, J. Li, J. Wang, and J.J. Kai: Mater. Chem. Phys., 2019, vol. 221, pp. 138–43.
Y. Lu, Y. Dong, S. Guo, L. Jiang, H. Kang, T. Wang, B. Wen, Z. Wang, J. Jie, Z. Cao, H. Ruan, and T. Li: Sci. Rep., 2014, vol. 4, pp. 1–5.
Y. Lu, X. Gao, L. Jiang, Z. Chen, T. Wang, J. Jie, H. Kang, Y. Zhang, S. Guo, H. Ruan, Y. Zhao, Z. Cao, and T. Li: Acta Mater., 2017, vol. 124, pp. 143–50.
D. Choudhuri, B. Gwalani, S. Gorsse, R.S. Mishra, and R. Banerjee: Acta Mater., 2019, vol. 165, pp. 420–30.
W.H. Liu, Z.P. Lu, J.Y. He, J.H. Luan, Z.J. Wang, B. Liu, Y. Liu, M.W. Chen, and C.T. Liu: Acta Mater., 2016, vol. 116, pp. 332–42.
S. Dasari, Y. Chang, A. Jagetia, V. Soni, A. Sharma, B. Gwalani, S. Gorsse, A. Yeh, and R. Banerjee: Mater. Sci. Eng. A, 2021, vol. 805, p. 140551.
Y. Zeng, M. Man, K. Bai, and Y.W. Zhang: Mater. Des., 2021, vol. 202, p. 109532.
K. Kaufmann and K.S. Vecchio: Acta Mater., 2020, vol. 198, pp. 178–222.
M.R. Rahul and G. Phanikumar: Metall. Mater. Trans. A, 2019, vol. 50A, pp. 2594–98.
R. Li, L. Xie, W.Y. Wang, P.K. Liaw, and Y. Zhang: Front. Mater., 2020, vol. 7, pp. 1–2.
A. Raturi, J.C. Aditya, N.P. Gurao, and K. Biswas: J. Alloys Compd., 2019, vol. 806, pp. 587–95.
L. Zhang, M. He, and S. Shao: Nano Energy, 2020, vol. 78, p. 105380.
Y. Liu, B. Guo, X. Zou, Y. Li, and S. Shi: Energy Storage Mater., 2020, vol. 31, pp. 434–50.
T. Wang, C. Zhang, H. Snoussi, and G. Zhang: Adv. Funct. Mater., 2020, vol. 30, pp. 1–4.
Y.J. Chang, C.Y. Jui, W.J. Lee, and A.C. Yeh: J. Met., 2019, vol. 71, pp. 3433–42.
L. Zhang, H. Chen, X. Tao, H. Cai, J. Liu, Y. Ouyang, Q. Peng, and Y. Du: Mater. Des., 2020, vol. 193, p. 108835.
N. Islam, W. Huang, and H.L. Zhuang: Comput. Mater. Sci., 2018, vol. 150, pp. 230–35.
S.M. Lundberg, G.G. Erion, and S. Lee: arXiv:1802.03888v3.
J.M. Rickman: NPJ Comput. Mater., 2018, vol. 5, pp. 1–8.
S. Gorsse, M.H. Nguyen, O.N. Senkov, and D.B. Miracle: Data Brief, 2018, vol. 21, pp. 2664–78.
M.L. Waskom: J. Open Source Softw., 2021, vol. 6, p. 3021.
J. Schmidt, M.R.G. Marques, S. Botti, and M.A.L. Marques: NPJ Comput. Mater., 2019, vol. 5, p. 83.
D.R. Cutler, T.C. Edwards, K.H. Beard, A. Cutler, K.T. Hess, J. Gibson, and J.J. Lawler: Ecology, 2007, vol. 88, pp. 2783–92.
K.Q. Weinberger, F. Sha, and L.K. Saul: Proc. 21st Int. Conf. Mach. Learn., 2004.
B. Schölkopf, A. Smola, and K.-R. Müller: in Artificial Neural Networks—ICANN ’97, W. Gerstner, A. Germond, M. Hasler, and J.-D. Nicoud, eds., Springer, Berlin, 1997, pp. 583–88.
Q. Wang: 2014. arXiv:1207.3538.
N. Shah, M.R. Rahul, S. Bysakh, and G. Phanikumar: Mater. Sci. Eng. A, 2021, vol. 824, p. 141793.
M.R. Rahul and G. Phanikumar: Mater. Sci. Eng. A, 2020, vol. 777, p. 139022.
T. Huang, J. Zhang, J. Zhang, and L. Liu: Appl. Sci., 2021, vol. 11, p. 6102.
One of the authors (ASB) acknowledges Ujjawal Kumar Jaiswal and Yegi Vamsi Krishna for their help with the algorithm development and for useful discussions. RMR acknowledges Professor G. Phanikumar (Department of Metallurgical and Materials Engineering, IIT, Madras) for providing research facilities and for useful discussions and Naishalkumar Shah for helpful communications.
On behalf of all of the authors, the corresponding author states that there is no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Bundela, A.S., Rahul, M.R. Application of Machine Learning Algorithms With and Without Principal Component Analysis for the Design of New Multiphase High Entropy Alloys. Metall Mater Trans A 53, 3512–3519 (2022). https://doi.org/10.1007/s11661-022-06764-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11661-022-06764-5