A Neural Networks Model for Accurate Prediction of the Flash Point of Chemical Compounds

Flashpoint is one of the most important flammability characteristics of chemical compounds. In the present study, we developed a neural network model for accurate prediction of the flashpoint of chemical compounds, using the number of hydrogen and carbon atoms, critical temperature, normal boiling point, acentric factor, and enthalpy of formation as model inputs. Using a robust strategy to efficiently assign neural network parameters and evaluate the authentic performance of the neural networks, we could achieve an accurate model that yielded average absolute relative errors of ۰. ۹۷, ۰. ۹۶, ۰.۹۹ and ۱.۰% and correlation coefficients of ۰.۹۹۸۴, ۰.۹۹۸۵, ۰.۹۹۸۱ and ۰.۹۹۷۹ for the overall, training, validation and test sets, respectively.  These results are among the most accurate ever reported ones, to date.

کلیدواژه ها:

Flashpoint ، predictive models ، Neural Networks ، QSPR ، Group contribution method