Martensite Variant Identi�cation For Shape Memory Alloys By Using Graph Neural Networks

Detailed microstructure evolution in shape memory alloys (SMAs) is typically studied by molecular dynamics (MD) simulations. However, the conventional post-processing tools for atomistic calculations, such as CNA and PTM, fail to identify distinct crystal variants and to reveal twin alignments in SMAs. In the current work, a powerful and efficient post-processing tool based on GraphSAGE neural network is developed, which can identify multiple phases in martensitic transformation, including the orthorhombic, monoclinic and R phases. Where the network was trained by the results of sets of temperature-and stress-induced martensitic transformation MD calculations. The accuracy and generality were also verified by the application to the cases which did not appear in the training dataset, such as unrecoverable nanoindentation process. The proposed method is rapid, accurate, and is ready to be integrated with any visualization tool for MD simulations. The outcome of the current work is expected to accelerate the pace of atomistic studies on SMAs and related materials.

[1]  Chih-Hsuan Chen,et al.  The Analysis of Superelasticity and Microstructural Evolution in NiTi Single Crystals by Molecular Dynamics , 2018, Materials.

[2]  Connor W. Coley,et al.  A graph-convolutional neural network model for the prediction of chemical reactivity , 2018, Chemical science.

[3]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[4]  Chee Kai Chua,et al.  A Review of Selective Laser Melted NiTi Shape Memory Alloy , 2018, Materials.

[5]  Lei Jia,et al.  Chemi-Net: A Molecular Graph Convolutional Network for Accurate Drug Property Prediction , 2018, International journal of molecular sciences.

[6]  A. Cuschieri,et al.  Low power consumption mini rotary actuator with SMA wires , 2017 .

[7]  Zhenpeng Zhou,et al.  Graph Convolutional Networks for Molecules , 2017, ArXiv.

[8]  A. Simone,et al.  Modeling pseudo-elasticity in NiTi: Why the MEAM potential outperforms the EAM-FS potential , 2017 .

[9]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[10]  Nien-Ti Tsou,et al.  Microstructural analysis and molecular dynamics modeling of shape memory alloys , 2017 .

[11]  Yunzhi Wang,et al.  An origin of functional fatigue of shape memory alloys , 2017 .

[12]  S. Schmidt,et al.  Robust structural identification via polyhedral template matching , 2016, 1603.05143.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  A. Stukowski.  Structure identification methods for atomistic simulations of crystalline materials , 2012, 1202.5005.

[15]  T. Antretter,et al.  Competing accommodation mechanisms of the martensite in nanocrystalline NiTi shape memory alloys , 2008 .

[16]  J. Ericksen,et al.  On the Cauchy—Born Rule , 2008 .

[17]  Dimitris C. Lagoudas,et al.  Aerospace applications of shape memory alloys , 2007 .

[18]  L. Brinson,et al.  Shape memory alloys, Part I: General properties and modeling of single crystals , 2006 .

[19]  X. Ren,et al.  Physical metallurgy of Ti–Ni-based shape memory alloys , 2005 .

[20]  B. Brackett.  New developments , 1987, Nature.

[21]  Tomoyuki Kakeshita,et al.  Science and Technology of Shape-Memory Alloys: New Developments , 2002 .

[22]  Michael I. Baskes,et al.  Second nearest-neighbor modified embedded-atom-method potential , 2000 .

[23]  Hannes Jónsson,et al.  Systematic analysis of local atomic structure combined with 3D computer graphics , 1994 .

[24]  J. van Humbeeck,et al.  Hysteresis Effects During Martensitic Transformation in Cu-Zn-Al Studied by Internal Friction Measurements , 1991 .

[25]  H. C. Andersen,et al.  Molecular dynamics study of melting and freezing of small Lennard-Jones clusters , 1987 .

[26]  J. Perkins.  Residual stresses and the origin of reversible (two-way) shape memory effects , 1974 .

[27]  J. V. Gilfrich,et al.  Effect of Low‐Temperature Phase Changes on the Mechanical Properties of Alloys near Composition TiNi , 1963 .

[28]  Arne. Olander.  AN ELECTROCHEMICAL INVESTIGATION OF SOLID CADMIUM-GOLD ALLOYS , 1932 .

[29]  Hsin-Yu Chen,et al.  The Analysis of Thermal-Induced Phase Transformation and Microstructural Evolution in Ni-Ti Based Shape Memory Alloys By Molecular Dynamics , 2019, Computer Modeling in Engineering & Sciences.

[30]  Antonio Concilio,et al.  Shape memory alloy engineering : for aerospace, structural and biomedical applications , 2014 .

[31]  A. Stukowski.  Modelling and Simulation in Materials Science and Engineering Visualization and analysis of atomistic simulation data with OVITO – the Open Visualization Tool , 2009 .

[32]  K. Bhattacharya.  Microstructure of martensite : why it forms and how it gives rise to the shape-memory effect , 2003 .

[33]  T. W. Duerig,et al.  An Introduction to Martensite and Shape Memory , 1990 .

[34]  P. Chadwick.  Continuum Mechanics: Concise Theory and Problems , 1976 .

[35]  T. Read,et al.  Plastic Deformation and Diffusionless Phase Changes in Metals — the Gold-Cadmium Beta Phase , 1951 .