Prediction of the flash points of alkanes by group bond contribution method using artificial neural networks

A group bond contribution model using artificial neural networks was established to predict the flash points of alkanes. Information of group property and connectivity in molecules was contained in the model, and 16 group bonds were used as input parameters of neural networks to study the correlation of molecular structures with flash points of 44 alkanes. The results show that the predicted flash points are in good agreement with the experimental data, with the absolute mean absolute error being 6.0 K, and the absolute mean relative error being 2.15%, which are superior to those of traditional group contribution methods. The method proposed can be used not only to reveal the quantitative relation between flash points and molecular structures of alkanes but also to predict the flash points of organic compounds for chemical engineering.