Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning

Zong, Hongxiang; Pilania, Ghanshyam; Ding, Xiangdong; Ackland, Graeme; Lookman, Turab

doi:10.1038/s41524-018-0103-x

Cited by 103 publications

(75 citation statements)

References 53 publications

(92 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a challenge with standard potentials. To-date ML-based potentials have been developed for many elemental systems such as Al 29,30 , Cu 31 30 , Fe 32 , Zr [33][34] Mo 35 , and Si 22,36 . In contrast, fewer versatile potentials for multi-element systems exist owing to the complexity of generating the DFT database as well as the optimization of the ML force-field.In the present study, we develop a deep neural net potential (DP) for the Cu-Zr binary alloy system using the DeepMD-Kit package 37 , and systematically analyze its fidelity in describing a wide range of properties and for different phases of the system.…”

mentioning

confidence: 99%

Optimization and validation of a deep learning CuZr atomistic potential: Robust applications for crystalline and amorphous phases with near-DFT accuracy

Andolina

Williamson

Saidi

2020

The Journal of Chemical Physics

View full text Add to dashboard Cite

We show that a deep-learning neural network potential (DP) based on density functional theory (DFT) calculations can well describe Cu-Zr materials, an example of a binary alloy system that can coexist in several ordered intermetallics and as an amorphous phase. The complex phase diagram for Cu-Zr makes it a challenging system for traditional atomistic force-fields that fail to describe well the different properties and phases. Instead, we show that a DP approach using a large database with ~300k configurations can render results generally on par with DFT. The training set includes configurations of pristine and bulk elementary metals and intermetallics in the liquid and solid phases in addition to slab and amorphous configurations. The DP model was validated by comparing bulk properties such as lattice constants, elastic constants, bulk moduli, phonon spectra, surface energies to DFT values for identical structures. Further, we contrast the DP results with values obtained using well-established two embedded atom method potentials. Overall, our DP potential provides near DFT accuracy for the different Cu-Zr phases but with a fraction of its computational cost, thus enabling accurate computations of realistic atomistic models especially for the amorphous phase. I.quenching rate. Both requirements pose a challenge for DFT simulations. Classical atomistic simulation methods, of which molecular dynamic simulations (MD) is the most common, have been employed in materials design for several decades to provide fast computations of atomic energies and forces. However, the parameters for these potentials to describe interatomic interactions are nontrivial to optimize. To date, the most accurate classical potentials for Cu-Zr systems are based on embedded atom method 12 (EAM) particularly those developed by Sheng et al. [13][14][15] (EAM-HS) and Mendeleev et al. 16 (EAM-MM) by fitting to a mixed experimental and ab-initio input data. While these two EAMs provide a general good description of many properties of Cu-Zr systems especially for properties that are included in the training such as the Cu-Zr melting curve as is the case of EAM-MM, they have limited transferability to configurations not included in the training as we demonstrate here. Further, and most importantly, EAM potentials have a limited functional form, and thus cannot be utilized to describe complex interactions such as for covalent and ionic bonds between Cu-Zr and reactive gasses.Machine learning (ML) and particularly deep neural network-based force-fields have the flexibility and non-linearity necessary to describe complex potential energy surfaces. [17][18][19][20][21][22][23] In traditional atomistic force-field methods such as the EAMs, the complex potential energy surface is approximated using privileged functional forms that are selected based on physical motivation. On the other hand, ML potentials do not employ any explicit functional form for the dependence of the energies and forces on the atomic coordinates, but rather "learn" how atoms interac...

show abstract

mentioning

confidence: 99%

Optimization and validation of a deep learning CuZr atomistic potential: Robust applications for crystalline and amorphous phases with near-DFT accuracy

Andolina

Williamson

Saidi

2020

The Journal of Chemical Physics

View full text Add to dashboard Cite

show abstract

“…To overcome the finite size effects, we use machine learning to train a classical atomic interaction potential, which we then use to study the chain-melted state, but which also describes the rest of potassium's phase diagram very well. Recent developments in X-ray diagnostics of dynamic compression experiments allow confirmation of HG phase formation on the nanosecond time scale; (7) atomistic simulations of the shock propagation through such a material rely on a potential that is transferrable across all relevant phases (33)(34)(35)(36)(37).…”

mentioning

confidence: 99%

On the chain-melted phase of matter

Robinson

Zong²,

Ackland

et al. 2019

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

View full text Add to dashboard Cite

Various single elements form incommensurate crystal structures under pressure, where a zeolite-type “host” sublattice surrounds a “guest” sublattice comprising 1D chains of atoms. On “chain melting,” diffraction peaks from the guest sublattice vanish, while those from the host remain. Diffusion of the guest atoms is expected to be confined to the channels in the host sublattice, which suggests 1D melting. Here, we present atomistic simulations of potassium to investigate this phenomenon and demonstrate that the chain-melted phase has no long-ranged order either along or between the chains. This 3D disorder provides the extensive entropy necessary to make the chain melt a true thermodynamic phase of matter, yet with the unique property that diffusion remains confined to 1D only. Calculations necessitated the development of an interatomic forcefield using machine learning, which we show fully reproduces potassium’s phase diagram, including the chain-melted state and 14 known phase transitions.

show abstract

“…We developed a Gaussian process based machine-learning interatomic potential to describe the phase transformation behaviors. The potential is directly learned from big database of first principles calculations that are related to the properties of different phases, enabling us to produce good results for the elastic properties, hcp, ω and bcc phase transformation behaviors, and defect formation energies [30]. are first equilibrated to achieve a minimum energy state using the conjugate gradient method, and then annealed at 300 K to their equilibrium, defect-free, hcp state.…”

Section: Methodsmentioning

confidence: 99%

Nucleation mechanism for hcp→bcc phase transformation in shock-compressed Zr

Zong

Ding

et al. 2020

Phys. Rev. B

Self Cite

View full text Add to dashboard Cite

We present large-scale atomic simulations of shock induced phase transition in Zr assisted by machine learning method. The results indicate that there exists a critical piston velocity of U p ~ 0.85 km/s, above which the product phase has changed from ω to bcc. Unlike the case in Fe, the shock induced hcp→bcc nucleation mechanism in hcp-Zr single-crystal shows significant dependence of crystal orientation. For shock along [101 0] direction, the hcp phase directly transforms into bcc as expected. However, for shock compression along [0001] and [12 10] directions, the hcp→bcc transformation occurs in quite a different manner, i.e., Zr single crystal transforms into a disordered intermediate that subsequently exhibits ultrafast crystallization of bcc phase within the timescales of sub-nanosecond. We associate such presence of disordered intermediate structure with the sluggishness of shear stress relaxation, which leads to an elastic unstable condition of the crystal during the first few picoseconds of uniaxial compression, and suggests that the fewer possible shear planes (related to Burgers mechanism) for [0001] and [12 10] shock loading is an underlying factor for the orientation dependence.

show abstract

Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning

Cited by 103 publications

References 53 publications

Optimization and validation of a deep learning CuZr atomistic potential: Robust applications for crystalline and amorphous phases with near-DFT accuracy

Optimization and validation of a deep learning CuZr atomistic potential: Robust applications for crystalline and amorphous phases with near-DFT accuracy

On the chain-melted phase of matter

Nucleation mechanism for hcp→bcc phase transformation in shock-compressed Zr

Contact Info

Product

Resources

About