Machine learning prediction of the hardness of tool and mold steels

被引：0
|
作者：
Wang J. [1 ]
Sun S. [1 ]
He Y. [2 ]
Zhang T. [1 ]
机构：
[1] Materials Genome Institute, Shanghai University, Shanghai
[2] School of Materials Science & Engineering, Shanghai University, Shanghai
来源：
Zhongguo Kexue Jishu Kexue/Scientia Sinica Technologica | 2019年 / 49卷 / 10期
关键词：
Hardness prediction; Machine learning; Tool and mold steels;
D O I：
10.1360/SST-2019-0060
中图分类号：
学科分类号：
摘要：
Hardness is a major indicator of the quality of tool and mold steels (TMS). Analytic formulas of hardness versus compositions were proposed here by using hierarchical clustering (HC) and LASSO regressions, based on data of 79 brands of TMS. HC presents two large groups of TMS, which contain high and low concentrations of chromium. Then, LASSO regressions were applied on each group and the regression result with the lowest root mean square error in leave-one-out cross-validation was taken out as the theoretical prediction formula of hardness versus chemical composition feature. Furthermore, atomic features were selected from electronegativity, atomic radius, valence electron number, electron affinity, first ionization energy, etc. LASSO regressions of the data with the atomic features give another prediction formula. These results demonstrate the powerful ability of machine learning in the design of TMS. © 2019, Science Press. All right reserved.
引用
收藏
页码：1148 / 1158
页数：10
相关论文
共 9 条
  • [1] Xiong J., Zhang T.Y., Shi S.Q., Machine learning prediction of elastic properties and glass-forming ability of bulk metallic glasses, MRS Commun, 8, pp. 1-10, (2019)
  • [2] Agrawal A., Choudhary A., An online tool for predicting fatigue strength of steel alloys based on ensemble data mining, Int J Fatigue, 113, pp. 389-400, (2018)
  • [3] Aourag H., Prediction of superlattices ultra hard aluminum rare-earth intermetallic compounds, Jnl Comp Theo Nano, 11, pp. 589-595, (2014)
  • [4] Dey S., Dey P., Datta S., Design of novel age-hardenable aluminium alloy using evolutionary computation, J Alloys Compd, 704, pp. 373-381, (2017)
  • [5] Dey S., Sultana N., Dey P., Et al., Intelligent design optimization of age-hardenable Al alloys, Comput Mater Sci, 153, pp. 315-325, (2018)
  • [6] Just E., New formulas for calculating hardenability curves, Metal Progress, 95, pp. 87-88, (1969)
  • [7] Vermeulen W.G., Van Der Wolk P.J., De Weijer A.P., Et al., Prediction of Jominy hardness profiles of steels using artificial neural networks, J Mater Eng Perform, 5, pp. 57-63, (1996)
  • [8] Filetin T., Majetic D., Zmak I., Prediction the Jominy curves by means of neural network, Proceedings of the 4th ASM Heat Treatment and Surface Engineering Conference in Europe, pp. 353-361, (1998)
  • [9] Hastie T., Tibshirani R., Friedman J., The Elements of Statistical Learning: Data Mining, Inference, and Prediction, (2009)
1