Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Matter structure description method applicable to machine learning potential energy surface construction

A technology of machine learning and material structure, applied in the fields of computational chemistry and physics, can solve problems such as insufficient precision and low efficiency of quantum mechanical potential energy surface, and achieve the effect of overcoming insufficient precision, strong portability and versatility, and good predictive ability

Inactive Publication Date: 2018-09-14
FUDAN UNIV
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method overcomes the shortcomings of insufficient accuracy of the previous empirical potential function and the low efficiency of the potential energy surface of quantum mechanics. It has strong portability and versatility, and can achieve good prediction ability for different material systems.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Matter structure description method applicable to machine learning potential energy surface construction
  • Matter structure description method applicable to machine learning potential energy surface construction
  • Matter structure description method applicable to machine learning potential energy surface construction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Construction of metal platinum Pt global energy surface. The first-principle density functional potential energy surface and the potential energy surface random search algorithm were used to sample the global data set, and a total of 26063 structures were obtained, including bulk, layered, and cluster structures. The structural energy range of the data set is 6 electron Ford per atom (the energy reference point is the most stable structure of the global potential energy surface), the force range is 10 electron Ford per Angstrom, and the tension range is 260 MPa. Use the standard feature function set among the present invention as input information (total 42 feature functions, wherein 24 two-body feature functions, 16 three-body feature functions, 2 four-body sign functions), adopt the feedforward neural network to train the data Set, the obtained global potential energy surface accuracy is energy error 9.9 millielectron Ford per atom, force error 0.11 electron Ford per ...

Embodiment 2

[0076] Metal Oxide Manganese Oxide MnO x (including different valence states of Mn) the construction of the overall potential energy surface. The first-principle density functional potential energy surface and the potential energy surface random search algorithm were used to sample the global data set, and a total of 102,134 structures were obtained, including bulk, layered, and cluster structures. The structural energy range of the data set is 3.2 electron Ford per atom (the energy reference point is the most stable structure on the global potential energy surface), the force range is 40 electron Ford per Angstrom, and the tension range is 84 MPa. Use the standard feature function set in the present invention as input information (each element contains 104 feature functions altogether, wherein 48 two-body feature functions, 48 ​​three-body feature functions, 8 four-body sign functions), adopt feedforward neural The data set is trained by the network, and the accuracy of the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of computational chemistry and physics, and particularly discloses a matter structure description method applicable to machine learning potential energy surface construction. A series of characteristic functions can be constructed by the aid of input atomic coordinates and can be used as input information, and global potential energy surface data of matter systems can be trained by the aid of machine learning processes so as to obtain machine learning potential energy surfaces. Inter-atomic bond lengths and bond angles are used as basic variables ofthe characteristic functions, and power functions, truncation functions, spherical harmonic functions and triangle functions are combined with one another to construct atomic ambient environments with structure information of bond making, coordination and the like; the global potential energy surface data of the matter systems come from quantum-mechanical computation and contain large quantitiesof energy, force and stress information of different matter structures. The matter structure description method has the advantages that the characteristic functions have characteristics of coordinaterotation invariance, atomic exchange invariance, first-order and second-order derivative continuity and the like, and accordingly the matter structure description method is applicable to complicated multi-element matter systems; high-dimensional machine learning potential energy surfaces obtained by means of training on the basis of the characteristic functions can be used for material structure search, reaction mechanism prediction research and the like.

Description

technical field [0001] The invention belongs to the technical field of computational chemistry and physics, and specifically relates to a material structure description method suitable for machine learning high-precision potential energy surface construction, which is used to numerically distinguish the surrounding environment of atoms in a material system. Background technique [0002] Material structure prediction and chemical reaction path search are the core tasks of contemporary physical and chemical computational simulation research, and play an important role in understanding and predicting the thermodynamic and kinetic properties of materials. Due to the complexity of the material system, currently feasible computational simulation schemes generally rely on electronic structure calculations based on quantum mechanics to establish the relationship between the geometric structure and energy of the system, that is, the potential energy surface. However, the potential fu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F19/00
CPCG16C20/70G16C10/00
Inventor 刘智攀商城黄思达
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products