Neural network potential for Al-Mg-Si alloys

The 6000 series Al alloys, which include a few percent of Mg and Si, are important in automotive and aviation industries because of their low weight, as compared to steels, and the fact their strength can be greatly improved through engineered precipitation. To enable atomistic-level simulations of both the processing and performance of this important alloy system, a neural network (NN) potential for the ternary Al-Mg-Si has been created. Training of the NN uses an extensive database of properties computed using first-principles density functional theory, including complex precipitate phases in this alloy. The NN potential accurately reproduces most of the pure Al properties relevant to the mechanical behavior as well as heat of solution, solute-solute, and solute-vacancy interaction energies, and formation energies of small solute clusters and precipitates that are required for modeling the early stage of precipitation and mechanical strengthening. This success not only enables future detailed studies of Al-Mg-Si but also highlights the ability of NN methods to generate useful potentials in complex alloy systems.

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

[2]  Nongnuch Artrith,et al.  An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 , 2016 .

[3]  Gábor Csányi,et al.  Gaussian approximation potentials: A brief tutorial introduction , 2015, 1502.01366.

[4]  A. Strandlie,et al.  Detailed atomistic insight into the β″ phase in Al–Mg–Si alloys , 2014 .

[5]  Atsuto Seko,et al.  Sparse representation for a potential energy surface , 2014, 1403.7995.

[6]  Nongnuch Artrith,et al.  Neural network potentials for metals and oxides – First applications to copper clusters at zinc oxide , 2013 .

[7]  Grgoire Montavon,et al.  Neural Networks: Tricks of the Trade , 2012, Lecture Notes in Computer Science.

[8]  L. Hector,et al.  Solute strengthening from first principles and application to aluminum alloys , 2012 .

[9]  Germany,et al.  Neural network interatomic potential for the phase change material GeTe , 2012, 1201.2026.

[10]  P. Uggowitzer,et al.  Mechanisms controlling the artificial aging of Al-Mg-Si Alloys , 2011 .

[11]  Eun-Ha Kim,et al.  The modified embedded-atom method interatomic potentials and recent progress in atomistic simulations , 2010 .

[12]  Xiaozhi Wu,et al.  Ab initio calculations of generalized-stacking-fault energy surfaces and surface energies for FCC metals , 2010 .

[13]  Nack J. Kim,et al.  Atomistic Modeling of pure Mg and Mg―Al systems , 2009 .

[14]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[15]  Stefano de Gironcoli,et al.  QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials , 2009, Journal of physics. Condensed matter : an Institute of Physics journal.

[16]  L. Hector,et al.  Prediction of dislocation cores in aluminum from density functional theory. , 2008, Physical review letters.

[17]  G. Scuseria,et al.  Restoring the density-gradient expansion for exchange in solids and surfaces. , 2007, Physical review letters.

[18]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[19]  M. Baskes,et al.  Modified embedded-atom method interatomic potentials for the Mg-Al alloy system , 2006, cond-mat/0610602.

[20]  C. S. Hartley,et al.  Characterization and visualization of the lattice misfit associated with dislocation cores , 2005 .

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

[22]  E. Kaxiras,et al.  Generalized-stacking-fault energy surface and dislocation properties of aluminum , 1999, cond-mat/9903440.

[23]  H. W. Zandbergen,et al.  Structure Determination of Mg5Si6 Particles in Al by Dynamic Electron Diffraction Studies , 1997 .

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

[25]  Steve Plimpton,et al.  Fast parallel algorithms for short-range molecular dynamics , 1993 .

[26]  M. Payne,et al.  Stacking fault energies in aluminium , 1992 .

[27]  J. Soler,et al.  Defect energetics in aluminium , 1991 .

[28]  D. Vvedensky,et al.  The calculation of stacking fault energies in close-packed metals , 1990 .

[29]  D. Vanderbilt,et al.  Soft self-consistent pseudopotentials in a generalized eigenvalue formalism. , 1990, Physical review. B, Condensed matter.

[30]  Biswas,et al.  Simulated annealing of silicon atom clusters in Langevin molecular dynamics. , 1986, Physical review. B, Condensed matter.

[31]  H. Berendsen,et al.  Molecular dynamics with coupling to an external bath , 1984 .

[32]  M. Baskes,et al.  Embedded-atom method: Derivation and application to impurities, surfaces, and other defects in metals , 1984 .

[33]  H. Lipson,et al.  ERRATUM: The calibration of Debye-Scherrer X-ray powder cameras , 1941 .