Design and implementation of materials database for heat treatment process simulation

doi:10.13251/j.issn.0254-6051.2023.09.042

Abstract

Abstract: Material parameters are the crucial data support in heat treatment process simulation. However, at present, there is a lack of relevant material databases in China, and a few existing databases have problems such as low data accuracy, poor integrity, and inability to share data, they only distinguish materials based on chemical composition, which cannot meet the parameter requirements of heat treatment process simulation. Therefore, a data structure focusing on chemical composition and microstructure was designed, and an online special material database was also independently developed. The database optimizes the data storage structure according to the characteristics of material parameters required for heat treatment process simulation. Adopting B/S architecture design realizes data sharing and improves the convenience of data use. Furthermore, by using data mining technology, the database introduces four machine learning algorithms: multivariable linear regression, Bayesian linear regression, decision tree, and random forest, and establishes an innovative data extraction mechanism. The effective data extraction strategy can be determined through the application analysis of existing data, and then the actual data requires at present can be obtained, which preliminarily solves the problem of data missing currently, and strongly supports the development of heat treatment process simulation.

Key words: material database, heat treatment, machine learning, data mining

CLC Number:

TG156.6

Zhang Lunfeng, Wang Zhihan, Zhao Junyu, An Kang, Xu Jun, Gu Jianfeng. Design and implementation of materials database for heat treatment process simulation[J]. Heat Treatment of Metals, 2023, 48(9): 247-252.

References

[1]Karditsas P J, Lloyd G, Walters M, et al. The european fusion material properties database[J]. Fusion Engineering Design, 2006, 81(8/14): 1225-1229.
[2]李姿昕, 张能, 熊斌, 等. 材料科学数据库在材料研发中的应用与展望[J]. 数据与计算发展前沿, 2020, 2(2): 78-90.
Li Zixin, Zhang Neng, Xiong Bin, et al. Materials science database in material research and development: Recent applications and prospects[J]. Frontiers of Data and Computing, 2020, 2(2): 78-90.
[3]尹海清, 姜雪, 张瑞杰, 等. 材料科学数据共享网及其在材料行业创新发展中的应用[J]. 中国科技资源导刊, 2016, 48(3): 58-65, 71.
Yin Haiqing, Jiang Xue, Zhang Ruijie, et al. National materials scientific data sharing network and its application to innovative development of materials industries[J]. Chian Science and Technology Resources Review, 2016, 48(3): 58-65, 71.
[4]刘芳宁, 王越, 孙瑞侠. 材料数据库的现状与发展趋势[J]. 科技创新导报, 2018, 15(34): 149-151.
[5]杨丽, 苏航, 柴锋, 等. 材料数据库和数据挖掘技术的应用现状[J]. 中国材料进展, 2019, 38(7): 672-681, 650.
Yang Li, Su Hang, Chai Feng, et al. Material database and application status of data mining technology[J]. Materials China, 2019, 38(7): 672-681, 650.
[6]Varol T, Canakci A, Ozsahin S. Prediction of effect of reinforcement content, flake size and flake time on the density and hardness of flake AA2024-SiC nanocomposites using neural networks[J]. Journal of Alloys and Compounds, 2018, 739: 1005-1014.
[7]Hayajneh M T, Hassan A M, Mayyas A T. Artificial neural network modeling of the drilling process of self-lubricated aluminum/alumina/graphite hybrid composites synthesized by powder metallurgy technique[J]. Journal of Alloys and Compounds, 2009, 478(1/2): 559-565.
[8]Wilson G, Aruliah D A, Brown C T, et al. Best practices for scientific computing[J]. PLoS Biology, 2014, 12(1): 1001745.
[9]杨克功. 钢的等温转变曲线[M]. 哈尔滨: 黑龙江人民出版社, 1981.
[10]Faber F A, Hutchison L, Huang B, et al. Prediction errors of molecular machine learning models lower than hybrid dft error[J]. Journal of Chemical Theory and Computation, 2017, 13(11): 5255-5264.
[11]Moot T, Isayev O, Call R W, et al. Material informatics driven design and experimental validation of lead titanate as an aqueous solar photocathode[J]. Materials Discovery, 2016, 6: 9-16.
[12]文成. 基于机器学习的高熵合金成分设计与性能优化[D]. 北京: 北京科技大学, 2022.
[13]Li K Q, Liu Y, Kang Q. Estimating the thermal conductivity of soils using six machine learning algorithms[J]. International Communications in Heat and Mass Transfer, 2022, 136: 106139.
[14]Press C. Bayesian Data Analysis[M]. Third Edition. Crc Press, 2005.
[15]Huang X, Wang H, Xue W, et al. A combined machine learning model for the prediction of time-temperature-transformation diagrams of high-alloy steels[J]. Journal of Alloys and Compounds, 2020, 823: 153694.
[16]Speiser J L, Miller M E, Tooze J, et al. A comparison of random forest variable selection methods for classification prediction modeling[J]. Expert Systems with Applications, 2019, 134: 93-101.