Method for calculating molecular energy of ethane by deep learning

A deep learning and molecular technology, applied in chemical statistics, molecular entity identification, chemical machine learning, etc., can solve problems such as difficulty in obtaining satisfactory results, and achieve the effect of avoiding convergence problems and reducing impact.

Inactive Publication Date: 2019-01-04
DALIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Restricted by this feature, it is difficult to obtain satisfactory results in the application of complex molecular systems or multi-molecular 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
  • Method for calculating molecular energy of ethane by deep learning
  • Method for calculating molecular energy of ethane by deep learning
  • Method for calculating molecular energy of ethane by deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A method to calculate the energy of ethane molecules through deep learning, using the spatial coordinates and corresponding energies of 1000 different configurations of ethane molecules. In ethane molecule, the C-H bond length (r C1-H1 , r C1-H2 , r C1-H3 , r C2-H4 , r C2-H5 , r C2-H6 ) ranges from C-C bond length (r C1-C2 ) ranges from The bond angle formed by C-C-H in the molecule (θ C2-C1-H1 , θ C2-C1-H2 , θ C2-C1-H3 , θ C1-C2-H4 , θ C1-C2-H5 , θ C1-C2-H6 ,) The variation range is 111.2±5°; the bond angle formed by H-C-H (θ H1-C1-H2 , θ H1-C1-H3 , θ H2-C1-H3 , θ H4-C1-H5 , θ H4-C1-H6 , θ H5-C1-H6 ) range of 107.6±5°; each dihedral angle (φ H1-C1-C2-H4 , φ H1-C1-C2-H5 , φ H1-C1-C2-H6 , φ H2-C1-C2-H4 , φ H2-C1-C2-H5 , φ H2-C1-C2-H6 , φ H3-C1-C2-H4 , φ H3-C1-C2-H5 , φ H3-C1-C2-H6), the range of change is 0-360°. The molecular energies of ethane in different configurations were obtained by Quantum ESPRESSO chemical calculation software, and ...

Embodiment 2

[0070] This embodiment provides a preferred solution of the hardware platform and software environment of the present invention.

[0071] Choose the low-end i5-6500CPU@3.20GHz / NVIDIA Corporation GK208[GeForce GT730] / 4G Mem hardware platform to obtain higher general performance; the software environment is Linux kernel 4.9 / TensorFlow-GPU 1.8.0 (installed via pip ), the driver is CUDA 9.0 / cuDNN 7.1.

Embodiment 3

[0073] This embodiment provides a preferred scheme for selecting input data in the present invention.

[0074] The constructed dataset contains configurations of 1000 ethane molecules and their one-to-one corresponding energies. The configurations are expressed in Bohrpositions, and the energy unit is kJ / mol. This method avoids using the gradient descent method to calculate the minimized total energy while ensuring that the accuracy of calculating molecular energies increases as the training set increases, and compares the results with those calculated using the standard DFT approximation (PBE). The parameters of the ethane molecule are set to 11, which are: ∑r C-H , r C1-C2 , Σθ C-C-H , Σθ H-C-H ,∑cos3φ H-C-C-H , eleven parameters. Based on the PBE results, the optimized ethane molecular configuration (C-H bond length is The bond length of C-C bond is The bond angle formed by C-C-H is 111.2°; the bond angle formed by H-C-H is 107.6°; each dihedral angle i...

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 discloses a method for calculating molecular energy of ethane by deep learning, and belongs to the technical field of molecular energy calculation. The method comprises steps as follows:S1, an ethane molecule database is constructed; S2, m configurations and corresponding energy are selected randomly as a training group, and the other (1000-m) configurations and corresponding energyare taken as a testing group; S3, molecular space coordinates of the training group are converted to form a training group configuration parameter input matrix; S4, energy data of the training groupis extracted as a training output energy matrix and the training output energy matrix is in one-to-one correspondence with the training group configuration parameter input matrix; S5, a testing groupconfiguration parameter input matrix and an output energy matrix are constructed, and the line number of the matrixes is 1000-m; S6, the ethane molecule energy matrix E<calc> is obtained by calculation of double nervous layers. According to the method, the influence of a ratio of the training group to the testing group on accuracy of a training result is reduced.

Description

technical field [0001] The invention relates to the technical field of molecular energy calculation, in particular to a method for calculating the molecular energy of ethane through deep learning. Background technique [0002] The machine learning of contemporary artificial intelligence, in the field of molecular structure optimization and minimum energy calculation, has a remarkable feature that as the degree of freedom of the initial matrix increases, that is, the more complex the molecular structure, the greater the degree of freedom, and the training group and the test group must be increased. ratio for accurate results. Restricted by this feature, it is difficult to obtain satisfactory results in the application of complex molecular systems or multi-molecular systems. Contents of the invention [0003] In order to solve the defects in the prior art, the present invention provides a method for calculating the energy of ethane molecules through deep learning, which red...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16C20/70G16C20/20
Inventor 周立川崔洪光蒋瑞魏俊峰
Owner DALIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap