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

Method for predicting boiling point of polycyclic aromatic hydrocarbon compound based on molecular energy data

A polycyclic aromatic hydrocarbon and data prediction technology, applied in nuclear methods, chemical property prediction, complex mathematical operations, etc., can solve problems such as poor interpretability of results and many parameters, and achieve the effect of avoiding experiments, simple operation process, and cost reduction.

Inactive Publication Date: 2021-11-26
上海真谱信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of these studies use traditional chemometric methods, such as multiple linear regression and partial least squares regression, as modeling tools, and use structural parameters calculated by semi-empirical methods as molecular descriptors to establish the structure-activity relationship of the physical and chemical properties of PAHs. Models, these are semi-empirical methods, and their parameters are relatively large, which brings a certain amount of noise data, resulting in the accuracy of the results being questionable, and the interpretability of the results is relatively poor

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 predicting boiling point of polycyclic aromatic hydrocarbon compound based on molecular energy data
  • Method for predicting boiling point of polycyclic aromatic hydrocarbon compound based on molecular energy data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1: Based on 4 quantum chemical structure energy descriptors of 50 polycyclic aromatic hydrocarbons, the support vector machine regression structure-activity relationship prediction model of the boiling point of polycyclic aromatic hydrocarbons established, the modeling results are as follows figure 1 shown.

[0028] The support vector machine regression algorithm was used to perform regression modeling on 50 polycyclic aromatic hydrocarbon sample data, and a quantitative prediction model for the boiling point of polycyclic aromatic hydrocarbons was established. The correlation coefficient between the predicted value of the model and the true value in the literature was 0.99.

Embodiment 2

[0029] Embodiment 2: Based on 4 quantum chemical structure energy descriptors of 50 polycyclic aromatic hydrocarbons, the support vector machine regression structure-activity relationship prediction model of the boiling point of polycyclic aromatic hydrocarbons established, the internal cross-validation results of the model leave-one-out method are as follows figure 2 shown.

[0030] Using the support vector machine regression algorithm to perform regression modeling on 50 polycyclic aromatic hydrocarbon sample data, a quantitative prediction model for the boiling point of polycyclic aromatic hydrocarbons was established. The internal cross-validation results of the model showed that the correlation coefficient between the predicted value of the model and the true value in the literature was 0.98.

Embodiment 3

[0031] Example 3: Table 3 shows the newly collected 4 polycyclic aromatic hydrocarbon compounds, their 4 quantum chemical structure energy descriptors, mapping transformation data, and their boiling point prediction results.

[0032] molecular EHOMO ELUMO ΔE ETot Y 1

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

Polycyclic aromatic hydrocarbon refers to a compound in which more than two benzene rings are connected in a condensed ring form, and is an organic pollutant widely existing in the environment. Data reports related to physicochemical properties of polycyclic aromatic hydrocarbons in literatures are few, and even if data recorded in the literatures are insufficient in precision. The main reason is that the experiment for detecting the physicochemical properties of the polycyclic aromatic hydrocarbons is complicated and more difficult. In order to overcome the defects of a traditional method, molecular structures and electronic structures of a plurality of polycyclic aromatic hydrocarbons are calculated in a full-optimization manner by utilizing a first principle density functional theory method, basic data of energy descriptors of quantum chemistry are obtained, and then the basic data are mapped and combined to obtain intermediate data of the energy descriptors; and a structure-activity relationship model between the boiling point of the polycyclic aromatic hydrocarbon and the quantum chemical energy parameters is established by using a support vector regression method based on the intermediate data, and finally the boiling point of the newly collected polycyclic aromatic hydrocarbon sample is forecasted by using the established structure-activity relationship model.

Description

technical field [0001] The invention relates to the prediction of the boiling point of polycyclic aromatic hydrocarbon compounds, in particular to a method for predicting the boiling point of polycyclic aromatic hydrocarbon compounds based on molecular energy data. Background technique [0002] Polycyclic aromatic hydrocarbons refer to compounds in which two or more benzene rings are connected in the form of condensed rings, and are a class of organic pollutants widely present in the environment. Polycyclic aromatic hydrocarbons form thousands of different compounds because the hydrogen atoms on the benzene ring can be replaced by different groups. They are also the largest type of environmental carcinogens. Among more than 1,000 carcinogens, polycyclic aromatic hydrocarbons Accounted for more than 1 / 3. There are not many data reports on the physical and chemical properties of PAHs in the literature, and even the data recorded in the literature are not accurate enough. The...

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): G16C20/30G06N20/10G06F17/11
Inventor 周晶晶刘太昂刘太行刘振昌吴治富周央朱峰刘远刘婷婷朱鲁阳
Owner 上海真谱信息科技有限公司
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