Quantitative structure-property relationship studies for predicting flash points of alkanes using group bond contribution method with back-propagation neural network.

Models of relationships between structure and flash point of 92 alkanes were constructed by means of artificial neural network (ANN) using group bond contribution method. Group bonds were used as molecular structure descriptors which contained information of both group property and group connectivity in molecules, and the back-propagation (BP) neural network was employed for fitting the possible nonlinear relationship existed between the structure and property. The dataset of 92 alkanes was randomly divided into a training set (62), a validation set (15) and a testing set (15). The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. Simulated with the final optimum BP neural network [9-5-1], the results showed that the predicted flash points were in good agreement with the experimental data, with the average absolute deviation being 4.8K, and the root mean square error (RMS) being 6.86, which were shown to be more accurate than those of the multilinear regression method. The model proposed can be used not only to reveal the quantitative relation between flash points and molecular structures of alkanes, but also to predict the flash points of alkanes for chemical engineering.

[1]  Jouko Yliruusi,et al.  Prediction of physicochemical properties based on neural network modelling. , 2003, Advanced drug delivery reviews.

[2]  V. Vazhev,et al.  Estimation of flash points and molecular masses of alkanes from their IR spectra , 2006 .

[3]  Quantitative structure–property relationships and neural networks: correlation and prediction of physical properties of pure components and mixtures from molecular structure , 1999 .

[4]  K. Ohtaguchi,et al.  A method for estimating flash points of organic compounds from molecular structures. , 1991 .

[5]  Takahiro Suzuki,et al.  Quantitative Structure-Property Relationships for the Estimation of Boiling Point and Flash Point Using a Radial Basis Function Neural Network , 1999, J. Chem. Inf. Comput. Sci..

[6]  T. A. Albahri.  Flammability characteristics of pure hydrocarbons , 2003 .

[7]  Horng-Jang Liaw,et al.  The prediction of the flash point for binary aqueous-organic solutions. , 2003, Journal of hazardous materials.

[8]  W. Lyman.  Handbook of chemical property estimation methods , 1982 .

[9]  Ritu Jain,et al.  QSPR Analysis of Flash Points , 2001, J. Chem. Inf. Comput. Sci..

[10]  Frank P. Lees,et al.  Loss Prevention In The Process Industries , 1980 .

[11]  John Aurie Dean,et al.  Lange's Handbook of Chemistry , 1978 .

[12]  Horng-Jang Liaw,et al.  A general model for predicting the flash point of miscible mixtures. , 2006, Journal of hazardous materials.

[13]  Igor V. Tetko,et al.  Neural network studies, 1. Comparison of overfitting and overtraining , 1995, J. Chem. Inf. Comput. Sci..