| Abstract
| - A neural network based quantitative structure−property relationship (QSPR) was developed for the vaporpressure−temperature behavior of hydrocarbons based on a data set for 274 compounds. The optimal QSPRmodel was developed based on a 7-29-1 back-propagation neural network architecture using valance molecularconnectivity indices (1χv, 3χv, 4χv), molecular weight, and temperature as input parameters. The averageabsolute errors in vapor pressure predictions for the test, validation, and overall data sets were 8.2% (0.036log P units or 23.2 kPA), 9.2% (0.039 log P units or 26.8 kPA), and 10.7% (0.046 log P units or 31.1 kPA),respectively. The performance of the QSPR for temperature-dependent vapor pressure, which was developedfrom a simple set of molecular descriptors, displayed accuracy of better than or well within the range ofother available estimation methods.
|
