Prediction of glass forming ability in amorphous alloys based on different machine learning algorithms

Abstract In this work, we adopted four machine learning (ML) models, i.e., random forest (RF), K nearest neighbor (KNN), gradient boosted decision trees (GBDTs) and eXtreme gradient boosting (XGBoost) to predict the glass forming ability (GFA) of amorphous alloys using the dataset of Deng. The critical casting diameter (Dmax) of these alloys represents their GFA. The correlation coefficient (R) and root mean square error (RMSE) of the RF, KNN, GBDTs as well as XGBoost models are 0.75 and 3.29, 0.734 and 3.431, 0.724 and 3.474, and 0.755 and 3.277, respectively. Based on 10-fold cross-validation, it is found that the XGBoost model exhibits the highest predictive performance than the other above-mentioned three ML models and twelve previously reported criteria. Our results imply that machine learning method is very powerful and efficient, and has great potential for designing new amorphous alloys with desired GFA.

[1]  X. Ji,et al.  A Thermodynamic Approach to assess glass-forming Ability of Bulk Metallic Glasses , 2009 .

[2]  Shihui Bao,et al.  A new criterion for evaluating the glass-forming ability of bulk glass forming alloys , 2008 .

[3]  B. S. Murty,et al.  On the parameters to assess the glass forming ability of liquids , 2005 .

[4]  H. Fan,et al.  A new criterion for evaluating the glass-forming ability of bulk metallic glasses , 2006 .

[5]  Mathieu Bauchy,et al.  Predicting the Young’s Modulus of Silicate Glasses using High-Throughput Molecular Dynamics Simulations and Machine Learning , 2019, Scientific Reports.

[6]  W. Wang,et al.  Machine Learning Approach for Prediction and Understanding of Glass-Forming Ability. , 2017, The journal of physical chemistry letters.

[7]  Ruijie Deng,et al.  A new mathematical expression for the relation between characteristic temperature and glass-forming ability of metallic glasses , 2020 .

[8]  Jie Xiong,et al.  A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys , 2020, Materials & Design.

[9]  M. K. Tripathi,et al.  Evolution of glass forming ability indicator by genetic programming , 2016 .

[10]  Shao-xiong Zhou,et al.  A new criterion for predicting glass forming ability of bulk metallic glasses and some critical discussions , 2011 .

[11]  Zhaoping Lu,et al.  The correlation between reduced glass transition temperature and glass forming ability of bulk metallic glasses , 2000 .

[12]  Z. Long,et al.  A new correlation between the characteristics temperature and glass-forming ability for bulk metallic glasses , 2018, Journal of Thermal Analysis and Calorimetry.

[13]  Zhilin Long,et al.  A new criterion for predicting the glass-forming ability of alloys based on machine learning , 2021 .

[14]  D. Turnbull.  Under what conditions can a glass be formed , 1969 .

[15]  A. Inoue,et al.  Mg–Cu–Y Amorphous Alloys with High Mechanical Strengths Produced by a Metallic Mold Casting Method , 1991 .

[16]  C. Liu,et al.  A new glass-forming ability criterion for bulk metallic glasses , 2002 .

[17]  A. Inoue,et al.  A new criterion for predicting the glass-forming ability of bulk metallic glasses , 2009 .