PREDICTION OF AUTOIGNITION TEMPERATURES OF ORGANIC-COMPOUNDS FROM MOLECULAR-STRUCTURE

A quantitative structure-property relationship study is performed to d evelop mathematical models that relate the structures of a heterogeneo us group of organic compounds to their autoignition temperature values . The molecular structures of the compounds are represented by calcula ted numerical descriptors which encode their topological, electronic, and geometric features. These descriptors are used to develop several multiple linear regression and computational neural network models to predict the autoignition temperatures of a data set consisting of hydr ocarbons, halohydrocarbons, and compounds containing oxygen, sulfur, a nd nitrogen. Both genetic algorithm and simulated annealing routines a re used to select subsets of descriptors based on multiple linear regr ession and computational neural networks. The models that are develope d have predictive ability in the range of the experimental error of au toignition temperature measurements.