A fast method for predicting the forbidden band width of polymers

A technology of forbidden band width and polymer, applied in the field of rapid prediction of the forbidden band width of polymers, can solve the problems of high test cost and low accuracy, and achieve the effects of convenient calculation, simple model and simple forbidden band width.

Active Publication Date: 2022-08-02
SHANGHAI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the prior art, the experimental methods for measuring the bandgap width include electrical variable temperature experiment, ultraviolet absorption spectrum experiment, photoelectric effect and photoexcitation spectrum. There are many factors affecting the bandgap width of samples measured in these experiments, including experimental instrument error, Operating error, sample lattice structure and impurity content, etc., and requires technical support of large instruments, the test cost is high and the accuracy is not high

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
  • A fast method for predicting the forbidden band width of polymers
  • A fast method for predicting the forbidden band width of polymers
  • A fast method for predicting the forbidden band width of polymers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] Example 1: The modeling results of the quantitative prediction model of polymer forbidden band width based on 228 first principles combined with support vector machines, such as figure 2 shown.

[0089] The regression modeling of 228 polymer sample data was carried out by using the support vector machine regression algorithm, and the quantitative prediction model of the support vector machine regression of the polymer forbidden band width was established. The coefficient of determination between the predicted value of the polymer band gap model and the first-principles calculated value is 0.9352.

Embodiment 2

[0090] Example 2: The leave-one-out internal cross-validation results of the quantitative prediction model of polymer forbidden band width based on 228 first principles combined with support vector machines, such as image 3 shown.

[0091] The leave-one-out method is used to carry out the internal cross-validation of the SVM quantitative prediction model of the polymer forbidden band width established by the 228 sample data. The coefficient of determination is 0.759.

Embodiment 3

[0092] Example 3: The independent test set prediction results of the quantitative prediction model of the polymer band gap based on 228 first principles combined with support vector machines, such as Figure 4 shown.

[0093] The 56 samples in the independent test set were predicted by using the support vector machine quantitative prediction model of the polymer forbidden band width, and good results were obtained. The coefficient of determination between the model predicted value and the first-principles calculated value of the polymer band gap is 0.8503.

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 relates to a method for rapidly predicting the forbidden band width of polymers. Based on the first principle combined with a support vector machine, the invention includes the following steps: searching for experimental values ​​of the structure and forbidden band width of polymers from literature; using different first principles Calculate the forbidden band width using the principle method, and select the optimal method; find the repeating unit from the literature and optimize the structure of the 4-module polymer; calculate the forbidden band width of the 4-module polymer; use the Dragon software to generate descriptors, data Divided into modeling set and test set; use the maximum correlation and minimum redundancy algorithm to screen variables, and use the support vector machine to build the model; according to the established model, quickly predict the forbidden band width of the polymer to be detected. The invention is based on reliable literature data and modeling methods, and the established prediction model of the forbidden band width of the polymer has the advantages of simplicity, speed, low cost, no pollution and the like.

Description

technical field [0001] The invention relates to the field of electrical properties of polymers, in particular to a method for rapidly predicting the forbidden band width of polymers. technical background [0002] A polymer is a compound with a large molecular weight formed by one or several simple small molecules through the polymerization reaction. Its molecular structure is formed by repeatedly connecting specific structural units through covalent bonds, and the relative molecular mass can be as high as Millions of them are quite different from small-molecule compounds in physical and chemical properties. Polymer materials include plastics, rubber, fibers, films, adhesives and coatings, etc. They have the characteristics of light weight, high strength, and good corrosion resistance, which are superior to other traditional structural materials, and are widely used in aviation, automobiles, ships, and infrastructure construction. , military supplies and other fields. [00...

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 Patents(China)
IPC IPC(8): G16C20/70G16C20/90
Inventor 徐鹏程卢天陆文聪
Owner SHANGHAI 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