|本期目录/Table of Contents|

[1]杨惠,陈利平,谢传欣,等.烃类及其衍生物闪点、沸点的定量构效关系[J].中国安全生产科学技术,2011,7(9):68-74.
 YANG Hui,CHEN Li-ping,XIE Chuan-xin,et al.QSPR study for predicting flash points and boiling points of hydrocarbon and their derivatives[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(9):68-74.
点击复制

烃类及其衍生物闪点、沸点的定量构效关系()
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
7
期数:
2011年9期
页码:
68-74
栏目:
学术论著
出版日期:
2011-09-30

文章信息/Info

Title:
QSPR study for predicting flash points and boiling points of hydrocarbon and their derivatives
文章编号:
1673-193X(2011)-09-0068-07
作者:
杨惠12陈利平2谢传欣1石宁1陈网桦2
1.化学品安全控制国家重点实验室,青岛 266071
2.南京理工大学化工学院安全工程系,南京 210094
Author(s):
YANG Hui12 CHEN Li-ping2 XIE Chuan-xin1 SHI Ning1 CHEN Wang-hua2
1.State Key Laboratory of Chemical Safety and Control, Qingdao 266071, China?
2.Department of Safety Engineering, School of Chemical Engineering, Nanjing University of Science & Technology, Nanjing 210094, China
关键词:
烃类及其衍生物闪点沸点支持向量机定量构效关系
Keywords:
Hydrocarbon and their derivatives Flash point Boiling point Support vector machine(SVM) QSPR
分类号:
O622.1
DOI:
-
文献标志码:
A
摘要:
基于定量结构-性质相关性(QSPR)原理,研究了烃类及其衍生物闪点、沸点与其分子结构间的内在定量关系。应用CODESSA软件计算384种烃类及其衍生物的分子结构描述符,建立了闪点和沸点的QSPR模型。用最佳多元线性回归(B-MLR)方法筛选得到的分子描述符建立了线性回归模型。用B-MLR方法所选择的5个描述符作为支持向量机(SVM)的输入建立了非线性模型。所有的化合物被分为训练集和测试集,对每个模型的训练集和测试集的复相关系数、交互验证系数、均方根误差等进行了计算,并用测试集对模型的预测能力进行检验,预测结果表明:预测值与实验值均符合良好,所建立的闪点模型稳健,泛化能力强,预测误差小,预测的效果令人满意,但沸点的模型预测效果有待加强。相比烃类物质的模型,加了衍生物的模型性能均有所下降。
Abstract:
The quantitative relationships existed between flash points、boiling points and molecular structures of hydrocarbon and their derivatives were investigated based on the quantitative structure-property relationship(QSPR) study. 384 molecular descriptors of hydrocarbon and their derivatives were calculated by CODESSA, and these descriptors were pre-selected by best multilinear regression method. Then QSPR models about flash points and boiling points were built. As a result, the five-descriptor linear models were developed to describe the relationship between the molecular structures and the flash points or the boiling points. The non-linear regression models were built based on support vector machine using the five descriptors selected by best multilinear regression method.The compounds were divided into a training set and a test set. The squared correlation coefficient, cross-validation coefficient and mean squared error of each model were calculated. The test set is used to validate the prediction performance of the resulting models. The predicted results indicated that, the prediction results were in good agreement with the experimental values. The models of flash points had robustness, strong generative ability and small prediction error. The predicted results were satisfactory. But the predicted results of boiling points remain to be improved. Compared to the models of hydrocarbons, the performance of the models which added derivatives has been decreased. This paper can be very helpful to expand the applied scope of QSPR study.

参考文献/References:

[1]Jyrki Taskinen,Jouko Yliruusi.Prediction of physicochemical properties based on neural network modeling[J].Adv Drug Delivery Rev,2003,55:1163-1183.[2] 蒋军成,潘勇.QSPR在有机物燃烧特性预测中的应用和进展[J].南京工业大学学报,2007,29(6):102-110.Jiang Juncheng,Pan Yong.Advances and applications of quantitative structure property relationship studies in prediction of flammabile characteristic of compounds[J].Journal of Nanjing University of Technology,2007,29(6):102-110.[3]Farhad Gharagheizi.Prediction of upper flammability limit percent of pure compounds from their molecular structures[J].Journal of Hazardous Materials,2009,167:507-510.[4]Yong Pan,Juncheng Jiang,Rui Wang et al.Advantages of support vector machine in QSPR studies for predicting auto-ignition temperatures of organic compounds[J].Chemometrics and Intelligent Laboratory Systems,2008,92:169-178.[5]Farhad Gharagheizi,Mehdi Sattari.Prediction of Triple-Point Temperature of Pure Components Using their Chemical Structures[J].Ind.Eng.Chem.Res,2010,49:929-932.[6]Vapnik V.Statistical Learning Theory[M].New York:Wiley,1998.[7]Cortes C,Vapnik V.Support–Vector network[J].Machine Learning,1995,20:273-297.[8]吴少雄,黄恩洲.基于支持向量机的控制图模式识别[J].计算机应用,2007,27(1):61-64.Wu Shaoxiong,Huang Enzhou.Control chart patterns recognition based on support vector machine[J].Journal of Computer Applications,2007,27(1):61-64.[9]王晓丹,郑春颖,吴崇明等.一种新的SVM对等增量学习算法[J].计算机应用,2006,26(10):2440-2443.Wang Xiaodan,Zheng Chunying,Wu Chongming,et al.New algorithm for SVM-Based incremental learning[J].Journal of Computer Applications,2006,26(10):2440-2443.[10]Gunn S R,Brown M,Bossley K M.Network performance assessment for neurofuzzy data modeling[J].Lecture Notes in Computer Science,1997,1280:313-323.[11]周新奇,何勤,赵晨曦等.结构多样性化合物沸点QSPR模型研究[J].计算机与应用化学,2008,25(6):717-720.Zhou Xinqi,He Qin,Zhao Chenxi,et al.QSPR study for compounds with diversity structures[J].Computers and Applied Chemistry,2008,25(6):717-720.[12] 王青松,刘娟,徐美荣等.不饱和链烃沸点的QSPR研究[J].武汉理工大学学报,2006,28(3):117-120.Wang Qingsong,Liu Juan,Xu Meirong,et al.QSPR research on the boiling points of unsaturated chain hydrocarbons[J].Journal of Wuhan University of Technology,2006,28(3):117-120.[13]Tetteh J,Suzuki T,Metcalfe E,et al.Quantitative structure-property relationships for the estimation of boiling point and flash point using a radial basis function neural network[J].J Chem Inf Comput Sci,1999,39:491-507.[14]Espinosa G,Yaffe D,Cohen Y,et a1.Neural network based quantitative property relations (QSPRs)for predicting boiling points for aliphatie hydrocarbons[J].J Chem lnf Comput Sci,2000,40:859 -879.[15]Yong Pan,Juncheng Jiang,Zhirong Wang.Quantitative structure-property relationship for predicting flash points of alkanes using group bond contribution method with back-propagation neural network [J].Journal of Hazardous Materials,2007,147:424-430.[16]Alan R.Katritzky,Ruslan Petrukhin,and Ritu Jain.QSPR Analysis of Flash Point[J].J.Chem.Inf.Comput.Sci,2001,41:1521-1530.[17]潘勇,蒋军成.电性拓扑状态指数预测烃类物质闪点[J].石油学报(石油加工),2007,23(6):70-74.Pan Yong,Jiang Juncheng.Prediction of flash point of hydrocarbon by electrotopological state indices[J].ACTA Petrolei Sinica(Petroleum processing section),2007,23(6):70-74.[18]Suhani J.Patel,Dedy Ng,M.Sam Mannan.QSPR Flash Point Prediction of Solvents Using Topological Indices for Application in Computer Aided Molecular Design[J].Ind.Eng.Chem. Res,2009,48:7378-7387.[19]Alan R.Katritzky,Iva B. Stoyanova-Slavova,Dimitar A. Dobchev.QSPR modeling of flash points : An update[J].Journal of Molecular Graphics and Modelling,2007,26:529-536.[20]Department of chemistry of university of akron.The Chemical Database[OB/OL].[2010-01-16].http://ull.chemistry.uakron.edu/erd/[21]Katritzky A.R,Perumal S,Petrukhin R et al.CODESSA-Base theoretical QSPR model for hydantoin HPLC-RT [J].J.Chem.Inf.Comput. Sci,2001,41:569-574.[22]Katritzky A.R,Lobanov V.S,Karelson M.CODESSA Version 2.0 Reference Manual[J].University of Florida.[23]Katritzky A.R,Kuanar M.,Fara D.C et al.QSPR treatment of rat blood: air, saline: air and olive oil: air partition coefficients using theoretical molecular descriptors[J].Bioorganic& Medicinal Chemistry,2004,12:4735-4748.[24]杨惠,陈利平,谢传欣等.烃类物质闪点定量构效的关系[J].计算机与应用化学,已录用.Yang Hui,Chen Liping,Xie Chuanxin,et al.Quantitative structure-property relationships for flash points of hydrocarbon compounds[J].Computers and Applied Chemistry.[25]杨惠,陈利平,谢传欣等.烃类沸点的定量构效关系研究[J].火灾科学,2011,20(1):62-67.Yang Hui,Chen Liping,Xie Chuanxin,et al.Quantitative structure-property relationships for boiling points of hydrocarbon compounds based on SVM[J].Fire Safety Science,2011,20(1):62-67.

相似文献/References:

[1]陈莹,蒋军成,潘勇,等.混合液体火灾爆炸危险性——闪点预测与实验研究[J].中国安全生产科学技术,2010,6(2):8.
 CHEN Ying,JIANG Jun-cheng,PAN Yong,et al.Fire and Explosion risk of mixture——flash point prediction and experimental study[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(9):8.

备注/Memo

备注/Memo:
收稿日期:2011-01-06
作者简介:杨惠,女,硕士研究生。
通讯作者:陈利平,女,博士。
基金项目:化学品安全控制国家重点实验室开放研究基金
更新日期/Last Update: