基于机器学习的Laves相生成焓预测研究

Abstract
Figure/Table
References
Related Citation (14)

Download:

Full Text ( PDF ) (4420KB)
Export: BibTeX | EndNote (RIS)

Abstract The determination of formation enthalpy is indispensable to the synthetic design of new Laves phase alloy materials. In recent years, in order to solve the problem of low efficiency in the determination of enthalpy of formation, a new model for predicting enthalpy of formation based on machine learning has received extensive attention. In this work, 21 machine learning regression models were constructed by three feature sets and seven regression algorithms. Based on the data set of formation enthalpy of Laves phase alloys collected from OQMD database, the effects of algorithm selection and feature selection on the overall performance of the model were systematically compared. The results show that the RF model has the highest comprehensive performance, which is higher than the prediction accuracy of Miedema semi-empirical model, and can quickly predict the formation enthalpy of Laves phase alloy. The influence of component characteristics on formation enthalpy is much greater than that of structure characteristics, and the influence of electron factors is greater than that of size factors. The DFT calculated value of formation enthalpy of Laves phase was added to the experimental data set to form a large sample data set, on which the accuracy of the ML model established was greatly improved. This method can be used for rapid preliminary screening of newly designed Laves phase alloy materials, thus improving the development progress of new Laves phase alloy.

Key words： Laves phase machine learning formation enthalpy regression model

Published: 05 June 2022 Online: 2022-06-08

CLC number:

O642

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHAO Wei
	HUA Fu'an
	LI Jianping

Cite this article:

ZHAO Wei,HUA Fu'an,LI Jianping. Study on Prediction of Formation Enthalpy of Laves Phase Alloys Based on Machine Learning[J]. Materials Reports, 2022, 36(Z1): 21120179-5.

URL:

http://www.mater-rep.com/EN/ OR http://www.mater-rep.com/EN/Y2022/V36/IZ1/21120179

1 Guo Q T, Kleppa O J. Journal of Alloys and Compounds, 2001, 321(2), 169.
2 Kim G, Meschel S V, Nash P, et al. Scientific Data, 2017, 4, 162.
3 Zhang R F, Sheng S H, Liu B X. Chemical Physics Letters, 2007, 442, 511.
4 吴春峰, 李慧改, 郑少波, 等.上海金属, 2011, 33(4), 1.
5 周志敏, 孙艳蕊.东北大学学报(自然科学版), 2013, 34(11), 1585.
6 Kirklin S, Saal J E, Meredig B, et al. npj Computational Materials, 2015, 1, 15010.
7 Saal J E, Kirklin S, Aykol M, et al. Journal of Metals, Materials and Minerals, 2013, 65(11), 1501.
8 Ong S P, Cholia S, Ceder G, et al. Computational Materials Science, 2015, 97, 209.
9 Jain A, Ong S P, Hautier G, et al. APL Materials, 2013, 1, 1.
10 Ward L, Agrawal A, Choudhary A, et al. npj Computational Materials, 2016, 2, 16028.
11 Ubaru S, Midlar A, Saad Y, et al. Physical Review B, 2017, 95, 21.
12 Sun S P, Yi D Q, Jiang Y, et al. Materials Chemistry and Physics, 2011, 126(3), 632.
13 李健聪, 王泰然, 舒武, 等.中国科学技术大学学报, 2020, 50(6), 844.
14 Eremin R A, Zolotarev P, Leisegang T, et al. AIP Conference Procee-dings, 2019, 2163(1), 020003.
15 Edirisuriya M D, Joshi R P, Kumar N, et al. ACS Applied Materials and Interfaces, 2020, 12, 26.
16 徐雅斌, 孙胜杰, 武装.含能材料, 2021, 29(1), 20.
17 Jha D, Choudhary K, Tavazza F, et al. Nature Communications, 2020, 11, 1.
18 Zheng X, Peng Z, Zhang R. Chemical Science, 2018, 9, 44.
19 Lotfi S, Zhang Z, Viswanathan G, et al. Matter, 2020, 3, 1.
20 Liu Y, Zhao T, Ju W, et al. Journal of Materiomics, 2017, 3, 3.
21 Villars P, Brandenburg K, Berndt M, et al. Journal of Alloys and Compounds, 2001, 317, 26.
22 鲁世强, 黄伯云, 贺跃辉, 等.材料工程, 2003, 5, 43.
23 鲁世强, 黄伯云, 贺跃辉, 等.材料导报, 2003(1), 11.
24 Kandavel M, Bhat V, Rougier A, et al. International Journal of Hydrogen Energy, 2008, 33, 14.
25 Kandavel M, Ramaprabhu S. International Journal of Hydrogen Energy, 2007, 32(5), 620.
26 Zhu J H, Liu C T, Pike L M, et al. Intermetallics, 2002, 10(6), 579.
27 Teixeira A L, Leal J P, Falcao A O. Journal of Cheminformatics, 2013, 5(1), 9.
28 Seko A, Hayashi H, Nakayama K, et al. Physical Review B, 2017, 95, 14.
29 Schutt K T, Glawe H, Brockherde F, et al. Physical Review B, 2013, 89(20), 163.
30 Ward L, Liu R, Krishna A, et al. Physical Review B, 2017, 96, 2.
31 Ward L, Dunn A, Faghaninia A, et al. Computational Materials Science, 2018, 152, 60.