Title :
Prediction of Gas Chromatographic Retention Index for Hydrocarbons in FCC Gasoline
Author :
Ding, Ling ; Zhang, Xiaotong ; Sun, Zhaolin ; Song, Lijuan ; Sun, Ting
Author_Institution :
Liaoning Key Lab. of Petrochem. Eng., Liaoning Shihua Univ., Fushun, China
fDate :
March 31 2009-April 2 2009
Abstract :
A series of hydrocarbons in FCC gasoline have been used to develop quantitative structure-retention relationships (QSRR) for their gas chromatographic retention index (RI) by using molecular descriptors which were calculated by Dragon software. QSRR models were built by adopting multiple linear regression (MLR) and artificial neural network (ANN). However, the results showed more or less the same quality with the predictive correlation coefficient R of 0.9952 and 0.9953 for MLR and ANN respectively. The obtained results told us that linear method is good enough to model the gas chromatographic retention index at least to the current dataset.
Keywords :
chemical engineering computing; chromatography; neural nets; petrochemicals; petroleum; petroleum industry; production engineering computing; regression analysis; Dragon software; FCC gasoline; artificial neural network; gas chromatographic retention index; hydrocarbons; molecular descriptors; multiple linear regression; quantitative structure retention relationships; Computer science; FCC; Hydrocarbons; Petroleum; Artificial Neural Network (ANN); Multiple Linear Regression (MLR); quantitative structure-retention relationships (QSRR); retention index (RI);
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
DOI :
10.1109/CSIE.2009.302
