Prediction of the lower flammability limits of organic compounds based on the quantitative structure-property relationship

The quantitative relationships between the lower flammability limit (LFL) and the molecular structures of organic compounds were investigated based on the quantitative structure-property relationship (QSPR). Various structural parameters were calculated to describe the structure characteristics of the molecules based on their structures. A set of structure parameters which have significant contribution to LFL were chosen as the molecular descriptors by employing the genetic multiple linear regression (GA-MLR) algorithm, and a linear prediction model was developed. Then the support vector machine (SVM) was employed to model the possible nonlinear relationship between the same selected descriptors and LFL, and the corresponding nonlinear prediction models for LFL of organic compounds based on the molecular structures were constructed. The models were tested by internal and external validations. The results show that, for both the models, the predicted LFL values agree well with the experimental ones, and the predicted errors are in the allowable range of the experimental errors.