Iranian Journal of Chemical Engineering (IJChE)

Abstract The design of installations in the chemical industry requires knowledge of the thermodynamic properties of liquid mixtures. In the absence of experimental data, accurate predictive methods are needed. In this work, the refractive index and the surface tension are experimentally determined at different temperatures and atmospheric pressure, for the binary and ternary systems of benzyl alcohol, n-hexanol and water, less studied in the literature. Two models were developed for the correlation of excess surface tension with composition, normalized temperature and refractive index. The statistical processing of the experimental data with the multiple linear regression method allowed the development of a model for which, in the validation stage, the correlation coefficient was 0.9086 and the standard deviation was 4.36. With the best performing neural model, a correlation coefficient of 0.9727 and a standard deviation of 2.14 were obtained in the validation stage.

Abstract Guanidine hydrochloride has been widely used in the initial recovery steps of active protein from the inclusion bodies in aqueous two-phase system (ATPS). The knowledge of the guanidine hydrochloride effects on the liquid-liquid equilibrium (LLE) phase diagram behavior is still inadequate and no comprehensive theory exists for the prediction of the experimental trends. Therefore the effect the guanidine hydrochloride on the phase behavior of PEG4000+ potassium phosphate+ water system at different guanidine hydrochloride concentrations and pH was investigated in this study. To fill the theoretical gaps, the typical of support vector machines was applied to the k-nearest neighbor method in order to develop a regression model to predict the LLE equilibrium of guanidine hydrochloride in the above mentioned system. Its advantage is its simplicity and good performance, with the disadvantage of an increase the execution time. The results of our method are quite promising: they were clearly better than those obtained by well-established methods such as Support Vector Machines, k-Nearest Neighbour and Random Forest. It is shown that the obtained results are more adequate than those provided by other common machine learning algorithms.