Physicochemical property of polybrominated diphenyl ethers by new path location index and neural network

堵锡华

doi:10.3969/j.issn.0438-1157.2014.04.003

您当前的位置：

首页 >

文章列表页 >

Physicochemical property of polybrominated diphenyl ethers by new path location index and neural network

更新时间：2025-12-10

- Physicochemical property of polybrominated diphenyl ethers by new path location index and neural network
- CIESC Journal Issue 4, Pages: 1169-1178(2014)
- 作者机构：
  
  徐州工程学院化学化工学院,江苏,徐州,221111
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0438-1157.2014.04.003
  CLC： 131O625
- Online First：05 April 2014，
  
  Published：05 April 2014
- 稿件说明：
移动端阅览
堵锡华. Physicochemical property of polybrominated diphenyl ethers by new path location index and neural network[J]. CIESC Journal, 2014, (4): 1169-1178.
DOI：

堵锡华. Physicochemical property of polybrominated diphenyl ethers by new path location index and neural network[J]. CIESC Journal, 2014, (4): 1169-1178. DOI： 10.3969/j.issn.0438-1157.2014.04.003.

摘要

基于溴取代基及共轭母体的结构特征，定义一种新的路径定位指数mP，并计算了209种多溴联苯醚分子的电性拓扑状态指数E9和电性距离矢量M26，这3个指数对有机污染物呈现出良好的结构选择性。采用多元回归方法对多溴联苯醚（PBDEs）的色谱保留时间（tR）、正辛醇/空气分配系数（lgKOA）、超冷流体蒸气压（lgPL）及其毒性等性质与分子结构指数进行关联，建立的4个预测模型的相关系数分别达到0.991、0.997、0.998和0.904，标准偏差分别为0.031、0.104、0.100和0.358。将3个指数作为BP神经网络的输入层神经元，采用不同的网络体系结构，获得了令人满意的预测理化性质的神经网络模型，所得结果明显优于多元回归方法，结果显示多溴联苯醚的理化性质与0P、E9和M26具有良好的非线性关系。

Abstract

Based on the structure characteristics of bromine substituents and conjugated matrix

a new path location index mP is defined. The electrotopological state indices (E9) and electronegativity distance vector (M26) of 209 polybrominated diphenyl ethers (PBDEs) are calculated. It shows that mP

E9 and M26 have good structural selectivity for organic pollutant. Then

the multiple regression method is used to establish relationships between the molecular structure of PBDEs and four parameters: gas-chromatographic relative retention time (tR)

n-octanol pair partition coefficient (lgKOA)

supercooled liquid vapour pressures (lgPL) and toxicity (lgI). With the four predictive models

the correlation coefficients are 0.991

0.997

0.998 and 0.904 with the standard deviation of 0.031

0.104

0.100 and 0.358

respectively. Three structural parameters are used as the input neurons of the BP neural network and different network architectures to get several satisfying neural network models for predicting tR

lgKOA

and lgPL. The results are better than those by the multiple regression method

which shows significant nonlinear relationships between the physicochemical properties of PBDEs and the three structural parameters.

关键词

Keywords

references

Views

332

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of scale factor of heat exchangers based on CNN-LSTM neural network

Chemical process data imputation method based on DAT-MIGAN model

Leak localization method for gas pipeline based on TPE-XGBoost modeling

Contrastive learning based on method for identifying operating conditions of ethylene cracking furnace

Progress in research of selective oxidation of low carbon polyols over nano-Au catalysts with precise electronic effect regulation

Related Author

ZHANG Hanxiao

WANG Ruiqi

ZHANG Yating

ZHANG Hanxiao

ZHANG Yating

GENG Zhiqiang

LI Jiajun

WEI Wei

Related Institution

College of Chemistry and Chemical Engineering, Xi’an University of Science and Technology

College of Information Science and Technology, Beijing University of Chemical Technology

Engineering Research Center of Intelligent PSE, Ministry of Education of China

College of Petroleum and Natural Gas Engineering, Southwest Petroleum University

School of Petroleum Engineering, Chongqing University of Science and Technology

⁰