Estimation of Aniline Point Temperature of Pure Hydrocarbons: A Quantitative Structure−Property Relationship Approach

Abstract

In the present work, a quantitative structure−property relationship (QSPR) study is performed to predict the aniline point temperature of pure hydrocarbon components. As a powerful tool, genetic algorithm-based multivariate linear regression (GA-MLR) is applied to select most statistically effective molecular descriptors on the aniline point temperature of pure hydrocarbon components. Also, a three-layer feed forward neural network (FFNN) is constructed to consider the nonlinear behavior of appearing molecular descriptors in GA-MLR result. The obtained results show that the constructed FFNN can accurately predict the aniline point temperature of pure hydrocarbon components.

QSPR approach for determination of parachor of non-electrolyte organic compounds

“…The results of application of GA-MLR with RQK fitness function have been satisfactory in previous works (Gharagheizi and Sattari, 2010;Gharagheizi et al, 2009;Gharagheizi, 2007;Gharagheizi, 2009aGharagheizi, , 2009bGharagheizi, , 2009cGharagheizi, , 2009dGharagheizi and Mehrpooya, 2008;Gharagheizi and Alamdari, 2008;Gharagheizi, 2008aGharagheizi, , 2008bGharagheizi, , 2008cGharagheizi and Fazeli, 2008;Sattari and Gharagheizi, 2008;Vatani et al, 2007;Sattari, 2009a, 2009b;Gharagheizi and Mehrpooya, 2008). In order to perform GA-MLR, a program has been written in MATLAB s environment (Mathworks Inc. software).…”

“…Besides, RQK is a constrained fitness function based on Q 2 LOO statistics (leave-one-out cross validated variance) and other four tests that must be fulfilled contemporarily. This function is defined as follows (Gharagheizi and Sattari, 2010;Gharagheizi et al, 2009;Gharagheizi, 2007;Gharagheizi, 2009aGharagheizi, , 2009bGharagheizi, , 2009cGharagheizi, , 2009dGharagheizi and Alamdari, 2008;Gharagheizi, 2008aGharagheizi, , 2008bGharagheizi, , 2008cGharagheizi and Fazeli, 2008;Sattari and Gharagheizi, 2008;Vatani et al, 2007;Sattari, 2009a, 2009b;Gharagheizi and Mehrpooya, 2008):…”

A QSPR model for estimation of lower flammability limit temperature of pure compounds based on molecular structure

“…This methodology has been extensively presented in the previous works of the author and the results are satisfactory [4][5][6][7][8][9][10][11].…”

“…Molecular descriptors are computed only from chemical structure of a molecule using the known mathematical algorithms. Application of this methodology to correlate various physical and chemical properties has been showed promising results [4][5][6][7][8][9][10][11]. Therefore in this study, this methodology is used to develop a molecular-based model to predict LFLT of pure compounds.…”

Measurement and ANN prediction of pH-dependent solubility of nitrogen-heterocyclic compounds

“…Among the variety of ANN architectures, the feed-forward artificial neural network (FFNN) with an error back-propagation learning algorithm is the most commonly used network in simulating non-linear system (Liu and So, 2001;Gharagheizi et al, 2008;Mehrpooya et al, 2009). A schematic of a 3-layer ANN is shown in Fig.…”