Determination of Vapour Pressure of gasoline by double ANN algorithm combined with multidimensional gas chromatography

Abstract

In this paper, a double artificial neural network (ANN) algorithm has been established for calculating the Vapour Pressure of gasoline from the results of multidimensional gas chromatography analysis. Multidimensional resolution column was applied to obtain the results of the detailed hydrocarbon analysis of gasoline. The double ANN regression model has been established between the results of the detailed hydrocarbon analysis and the actually determined Vapour Pressure. When the method was applied to determine Vapour Pressure of export gasoline samples, the deviation of results was about 0.05 Psi (1 Psi=6.89KPa) compared with the standard method. The result of double ANN regression model was better than the result of partial least square (PLS) regression model. This method was easy to manipulate, and the modeling process was fast and easy to achieve. It was suitable for measuring the Vapour Pressure of the gasoline samples from the refinery and the export inspection.