Determination of the normal boiling point of chemical compounds using a quantitative structure-property relationship strategy: Application to a very large dataset

作     者：Gharagheizi, Farhad Mirkhani, Seyyed Alireza Ilani-Kashkouli, Poorandokht Mohammadi, Amir H. Ramjugernath, Deresh Richon, Dominique 

作者机构：Univ KwaZulu Natal Sch Engn Thermodynam Res Unit ZA-4041 Durban South Africa Islamic Azad Univ Dept Chem Engn Buinzahra Branch Buinzahra Iran IRGCP Paris France Aalto Univ Sch Sci & Technol Dept Biotechnol & Chem Technol Aalto Finland 

出 版 物：《FLUID PHASE EQUILIBRIA》 (流相平衡)

年 卷 期：2013年第354卷

页      面：250-258页

核心收录：

学科分类：081704[工学-应用化学] 07[理学] 0817[工学-化学工程与技术] 070304[理学-物理化学(含∶化学物理)] 08[工学] 0807[工学-动力工程及工程热物理] 0703[理学-化学] 

基　　金：South African Research Chairs Initiative of the Department of Science and Technology National Research Foundation 

主　　题：Normal boiling points QSPR Sequential forward search ANN Very large database 

摘      要：In this work, the quantitative structure property relationship (QSPR) strategy is applied to predict the normal boiling point (NBP) of pure chemical compounds. In order to propose a comprehensive, reliable, and predictive model, a large dataset of 17,768 pure chemical compounds was exploited. The sequential search mathematical method has been observed to be the only viable search method capable for selection of appropriate model parameters (molecular descriptors) with regard to a data set as large as is used in this study. To develop the model, a three-layer feed forward artificial neural network has been optimized using the Levenberg-Marquardt (LM) optimization strategy. Using this dedicated strategy, satisfactory results were obtained and are quantified by the following statistical parameters: average absolute relative deviations of the predicted properties from existing literature values: 3.2%, and squared correlation coefficient: 0.94. (C) 2013 Elsevier B.V. All rights reserved.