论文信息 - Prediction of the Watson Characterization Factor of Hydrocarbon Components from Molecular Properties

Prediction of the Watson Characterization Factor of Hydrocarbon Components from Molecular Properties

In the present work, a Quantitative Structure–Property Relationship (QSPR) study was performed to predict the Watson characterization factor of hydrocarbon components. A Genetic Algorithm-based Multivariate Linear Regression (GA-MLR) was applied to select the most statistically effective molecular descriptors of the Watson characterization factor. Then, based on the selected molecular descriptors by GA-MLR, a three-layer Feed Forward Neural Network (FFNN) was constructed to predict the Watson characterization factor. The obtained results showed that the constructed FFNN can accurately predict the Watson characterization factor of hydrocarbon components.

Farhad Gharagheizi | Ali Fazeli

[1] Mehdi Mehrpooya,et al. Prediction of standard chemical exergy by a three descriptors QSPR model , 2007 .

[2] Tareq A. Albahri. Molecularly Explicit Characterization Model (MECM) for Light Petroleum Fractions , 2005 .

[3] F. Gharagheizi,et al. Prediction of Standard Enthalpy of Formation by a QSPR Model , 2007, International Journal of Molecular Sciences.

[4] Farhad Gharagheizi,et al. QSPR analysis for intrinsic viscosity of polymer solutions by means of GA-MLR and RBFNN , 2007 .

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

[6] R. Boggia,et al. Genetic algorithms as a strategy for feature selection , 1992 .

[7] A. Katritzky,et al. How Chemical Structure Determines Physical, Chemical, and Technological Properties: An Overview Illustrating the Potential of Quantitative Structure−Property Relationships for Fuels Science , 2005 .

[8] Alan R. Katritzky,et al. Neural Networks Convergence Using Physicochemical Data , 2006, J. Chem. Inf. Model..