Predicting Pure Components Auto Ignition Temperature

T.A. Albahri and R.S. George (Kuwait)


Auto ignition, group contribution, neural networks.


A theoretical method for predicting the auto ignition temperature (AIT) of pure components is presented. Artificial neural networks were used to investigate several structural group contribution (SGC) methods available in the literature. The networks were used to probe the structural groups that have significant contribution to the overall AIT property of pure components and arrive at the set of groups that can best represent the auto ignition temperature of about 490 substances. The 58 structural groups listed were derived from the Ambrose, Joback and Chueh-Swanson definitions of group contributions and modified to account for the location of the functional groups in the molecule. The proposed method can predict the auto ignition temperature of pure components only from the knowledge of the molecular structure, with an average error of 2.8 % and a correlation coefficient of 0.98.

Important Links:

Go Back