Using machine learning and feature engineering to characterize limited material datasets of high-entropy alloys

Abstract The prediction of the phase formation of high entropy alloys (HEAs) has attracted great research interest recent years due to their superior structure and mechanical properties of single phase. However, the identification of these single phase solid solution alloys is still a challenge. Previous studies mainly focus on trial-and-error experiments or thermodynamic criteria, the previous is time consuming while the latter depends on the descriptors quality, both provide unreliable prediction. In this study, we attempted to predict the phase formation based on feature engineering and machine learning (ML) with a small dataset. The descriptor dimensionality is augmented from original small dimension to high dimension by non-linear combinations to characterize HEAs. The results showed that this method could achieve higher accuracy in predicting the phase formation of HEAs than traditional methods. Except the prediction of HEAs, this method also can be applied to other materials with limited dataset.

[1]  Elizabeth A. Holm,et al.  A Comparative Study of Feature Selection Methods for Stress Hotspot Classification in Materials , 2018, Integrating Materials and Manufacturing Innovation.

[2]  Yong Zhang,et al.  Amorphous phase formation rules in high-entropy alloys* , 2017 .

[3]  Akira Takeuchi,et al.  Quantitative evaluation of critical cooling rate for metallic glasses , 2001 .

[4]  Stefano Curtarolo,et al.  SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates , 2017, Physical Review Materials.

[5]  M. Marques,et al.  Recent advances and applications of machine learning in solid-state materials science , 2019, npj Computational Materials.

[6]  C. Liu,et al.  Effect of valence electron concentration on stability of fcc or bcc phase in high entropy alloys , 2011 .

[7]  B. Cantor,et al.  Microstructural development in equiatomic multicomponent alloys , 2004 .

[8]  Jian Lu,et al.  High-entropy alloy: challenges and prospects , 2016 .

[9]  Yong Zhang,et al.  Microstructural control and properties optimization of high-entrop alloys , 2012 .

[10]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[11]  Wei Li,et al.  Predicting the thermodynamic stability of perovskite oxides using machine learning models , 2018, Computational Materials Science.

[12]  Yong Zhang,et al.  Prediction of high-entropy stabilized solid-solution in multi-component alloys , 2012 .

[13]  D. Miracle,et al.  Mechanical properties of Nb25Mo25Ta25W25 and V20Nb20Mo20Ta20W20 refractory high entropy alloys , 2011 .

[14]  P. Liaw,et al.  High-entropy Alloys with High Saturation Magnetization, Electrical Resistivity, and Malleability , 2013, Scientific Reports.

[15]  M. Widom,et al.  Thermodynamics of concentrated solid solution alloys , 2017 .

[16]  Ron Kohavi,et al.  Feature Subset Selection Using the Wrapper Method: Overfitting and Dynamic Search Space Topology , 1995, KDD.

[17]  Chao Jiang,et al.  Efficient Ab initio Modeling of Random Multicomponent Alloys. , 2016, Physical review letters.

[18]  G. Pilania,et al.  Machine learning bandgaps of double perovskites , 2016, Scientific Reports.

[19]  Fritz Körmann,et al.  Impact of lattice relaxations on phase transitions in a high-entropy alloy studied by machine-learning potentials , 2018, npj Computational Materials.

[20]  B. S. Murty,et al.  Analysis of phase formation in multi-component alloys , 2012 .

[21]  Wenjiang Huang,et al.  Machine learning for phase selection in multi-principal element alloys , 2018, Computational Materials Science.

[22]  Yunhao Huang,et al.  Atomic-size effect and solid solubility of multicomponent alloys , 2015 .

[23]  Rampi Ramprasad,et al.  Adaptive machine learning framework to accelerate ab initio molecular dynamics , 2015 .

[24]  Liang Wang,et al.  Composition design of high entropy alloys using the valence electron concentration to balance strength and ductility , 2018 .

[25]  Ankit Agrawal,et al.  Machine learning approaches for elastic localization linkages in high-contrast composite materials , 2015, Integrating Materials and Manufacturing Innovation.

[26]  J. Yeh,et al.  Electrochemical kinetics of the high entropy alloys in aqueous environments—a comparison with type 304 stainless steel , 2005 .

[27]  Sheng Guo,et al.  Phase selection rules for cast high entropy alloys: an overview , 2015 .

[28]  N. P. Gurao,et al.  In the quest of single phase multi-component multiprincipal high entropy alloys , 2017 .

[29]  T. Shun,et al.  Nanostructured High‐Entropy Alloys with Multiple Principal Elements: Novel Alloy Design Concepts and Outcomes , 2004 .

[30]  D. Xue,et al.  Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models , 2020 .

[31]  Zhijun Wang,et al.  Phase Selection in High-Entropy Alloys: From Nonequilibrium to Equilibrium , 2014 .

[32]  Somnath Datta,et al.  Informatics-aided bandgap engineering for solar materials , 2014 .

[33]  Yuma Iwasaki,et al.  Machine-learning guided discovery of a new thermoelectric material , 2019, Scientific Reports.

[34]  Jien-Wei Yeh,et al.  Microstructure, thermophysical and electrical properties in AlxCoCrFeNi (0 ≤ x ≤2) high-entropy alloys , 2009 .

[35]  Jinlan Wang,et al.  Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning , 2018, Nature Communications.

[36]  D. Miracle,et al.  A critical review of high entropy alloys and related concepts , 2016 .

[37]  A. Clarke,et al.  High-Throughput Solid Solution Strengthening Characterization in High Entropy Alloys , 2018, Acta Materialia.

[38]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[39]  P. Rivera-Díaz-del-Castillo,et al.  A criterion for the formation of high entropy alloys based on lattice distortion , 2016 .

[40]  H. Zhuang,et al.  Machine-learning phase prediction of high-entropy alloys , 2019, Acta Materialia.

[41]  P. Liaw,et al.  Solid‐Solution Phase Formation Rules for Multi‐component Alloys , 2008 .

[42]  M. Widom,et al.  Prediction of A2 to B2 Phase Transition in the High-Entropy Alloy Mo-Nb-Ta-W , 2013, 1306.5043.

[43]  Deepak S. Turaga,et al.  Learning Feature Engineering for Classification , 2017, IJCAI.

[44]  C. Liu,et al.  Phase stability in high entropy alloys: Formation of solid-solution phase or amorphous phase , 2011 .

[45]  Steve Brown,et al.  Hume-Rothery for HEA classification and self-organizing map for phases and properties prediction , 2017 .

[46]  C. Liu,et al.  More than entropy in high-entropy alloys: Forming solid solutions or amorphous phase , 2013 .

[47]  Y. Tan,et al.  Design of high-entropy alloys with a single solid-solution phase: Average properties vs. their variances , 2018 .