Machine learning for hierarchical prediction of elastic properties in Fe-Cr-Al system

Abstract We apply extremely randomized trees and deep neural network to cluster expansion generated data to construct the hierarchical model that predicts the ternary properties using machine learning model trained by binary data. We focus on the elastic properties bulk modulus and shear modulus. By feeding composition and temperature as features and elastic property as target property into extremely randomized trees, the predictions of ternary alloys achieve the mean absolute errors of 0.56 GPa and 1.49 GPa in bulk modulus and shear modulus, respectively. The performance in shear modulus predictions can be improved by adding point probability that characters the ordering effect into feeding features. We find that the compositions and temperature are key features in bulk modulus, while compositions, temperature, and the ordering effect are important in shear modulus.

[1]  Lawrence O. Hall,et al.  A Comparison of Ensemble Creation Techniques , 2004, Multiple Classifier Systems.

[2]  R. W. Lynch,et al.  X-Ray Diffraction Studies of the Lattice Parameters of Solids under Very High Pressure , 1967 .

[3]  G. Kresse,et al.  Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set , 1996 .

[4]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[5]  Y. Lin,et al.  Prediction of metadynamic softening in a multi-pass hot deformed low alloy steel using artificial neural network , 2008 .

[6]  J. Kollár,et al.  High temperature oxidation of Fe-Al and Fe-Cr-Al alloys: The role of Cr as a chemically active element , 2010 .

[7]  H. Ledbetter,et al.  Elastic constants of monocrystal iron from 3 to 500 K , 2006 .

[8]  B. D. Conduit,et al.  Design of a nickel-base superalloy using a neural network , 2017, ArXiv.

[9]  Nikolai A Zarkevich,et al.  Reliable first-principles alloy thermodynamics via truncated cluster expansions. , 2004, Physical review letters.

[10]  Samad Hajinazar,et al.  Stratified construction of neural network based interatomic models for multicomponent materials , 2016, 1609.08455.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  H. Petrilli,et al.  Ab-initio calculations of the formation energies of BCC-based superlattices in the FeAl system , 2002 .

[13]  Stefanie Jegelka,et al.  Virtual screening of inorganic materials synthesis parameters with deep learning , 2017, npj Computational Materials.

[14]  Feng Lin,et al.  Machine Learning Directed Search for Ultraincompressible, Superhard Materials. , 2018, Journal of the American Chemical Society.

[15]  R. Kikuchi,et al.  Phase diagrams of FCC and BCC ordered alloys , 1974 .

[16]  M. Sanjari,et al.  Modeling of high temperature rheological behavior of AZ61 Mg-alloy using inverse method and ANN , 2008 .

[17]  Xiao Zhang,et al.  Phase diagrams and elastic properties of the Fe-Cr-Al alloys: A first-principles based study , 2019, Calphad.

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  S. Du,et al.  Development of interatomic potentials for Fe-Cr-Al alloy with the particle swarm optimization method , 2019, Journal of Alloys and Compounds.

[20]  Cormac Toher,et al.  Universal fragment descriptors for predicting properties of inorganic crystals , 2016, Nature Communications.

[21]  J. Rayne,et al.  Elastic Constants of Iron from 4.2 to 300°K , 1961 .

[22]  Wenjian Hu,et al.  Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination. , 2017, Physical review. E.

[23]  Ce Wang,et al.  Machine learning of frustrated classical spin models. I. Principal component analysis , 2017, 1706.07977.

[24]  D. I. Bolef,et al.  Anomalies in the Elastic Constants and Thermal Expansion of Chromium Single Crystals , 1963 .

[25]  Roger G. Melko,et al.  Machine learning phases of matter , 2016, Nature Physics.

[26]  C. M. Wayman,et al.  Shape-Memory Materials , 2018 .

[27]  A. Ruban,et al.  First-principles study of elastic properties of Cr- and Fe-rich Fe-Cr alloys , 2011 .

[28]  Lance Lewis Snead,et al.  Radiation tolerance of neutron-irradiated model Fe-Cr-Al alloys , 2015 .

[29]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[30]  Kresse,et al.  Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. , 1996, Physical review. B, Condensed matter.

[31]  Jeffrey C Grossman,et al.  Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[32]  Sreerama K. Murthy,et al.  Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey , 1998, Data Mining and Knowledge Discovery.

[33]  R. Kikuchi,et al.  Tetrahedron approximation of the cluster variation method for b.c.c. alloys , 1989 .

[34]  Mark R. Albing,et al.  A high-throughput investigation of Fe–Cr–Al as a novel high-temperature coating for nuclear cladding materials , 2015, Nanotechnology.

[35]  James H. Garrett,et al.  Knowledge-Based Modeling of Material Behavior with Neural Networks , 1992 .

[36]  Blöchl,et al.  Projector augmented-wave method. , 1994, Physical review. B, Condensed matter.

[37]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[38]  R. Hill.  The Elastic Behaviour of a Crystalline Aggregate , 1952 .

[39]  Marco Buongiorno Nardelli,et al.  The high-throughput highway to computational materials design. , 2013, Nature materials.

[40]  James Theiler,et al.  Accelerated search for materials with targeted properties by adaptive design , 2016, Nature Communications.

[41]  Kelvin George Chng,et al.  Unsupervised machine learning account of magnetic transitions in the Hubbard model. , 2017, Physical review. E.

[42]  Jamshid Ghaboussi,et al.  New nested adaptive neural networks (NANN) for constitutive modeling , 1998 .

[43]  Lei Wang,et al.  Discovering phase transitions with unsupervised learning , 2016, 1606.00318.