Original Article |
2012, Vol.34, No.5, pp. 569-575
Novel approach to predict the azeotropy at any pressure using classification by subgroups
Taehyung Kim, Hiromasa Kaneko, Naoya Yamashiro, and Kimito Funatsu
pp. 569 - 575
Abstract
Distillation is one of the dominating separation processes, but there are some problems as inseparable mixtures are formed in some cases. This phenomenon is called as azeotropy. It is essential to understand azeotropy in any distillation processes since azeotropes, i.e. inseparable mixtures, cannot be separated by ordinary distillation. In this study, to construct a model which predicts the azeotropic formation at any pressure, a novel approach using support vector machine (SVM) is presented. The SVM method is used to classify data in the two classes, that is, azeotropes and non-azeotropes. 13 variables, including pressure, were used as explanatory variables in this model. From the result of the SVM models which were constructed with data measured at 1 atm and data measured at all pressures, the 1 atm model showed a higher prediction performance to the data measured at 1 atm than the all pressure model. Thus, for improving the performance of the all pressure model, we focused on intermolecular forces of solvents. The SVM models were constructed with only data of the solvents having same subgroups. The accuracy of the model increased and it is expected that this proposed method will be used to predict azeotropic formation at any pressure with high accuracy