Prediction of Infinite Dilution Activity Coefficients of Halogenated Hydrocarbons in Water Using Classification and Regr
- PDF / 327,055 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 47 Downloads / 175 Views
Prediction of Infinite Dilution Activity Coefficients of Halogenated Hydrocarbons in Water Using Classification and Regression Tree Analysis and Adaptive Neuro-Fuzzy Inference Systems Kobra Zarei • Morteza Atabati
Received: 24 November 2010 / Accepted: 28 June 2012 / Published online: 5 March 2013 Ó Springer Science+Business Media New York 2013
Abstract A quantitative structure-infinite dilution activity relationship was developed to predict the infinite dilution activity coefficients of halogenated hydrocarbons, c?, in water at 298.15 K. A set of 1,497 zero-to three-dimentional descriptors were used for each molecule in the data set. Classification and regression tree (CART) were successfully used as a descriptor selection method. Three descriptors were selected and used as inputs for the adaptive neuro-fuzzy inference system (ANFIS). The root mean square errors for both calibration and prediction sets are 0.48. The results were compared with those obtained from other models. The results showed that CART-ANFIS can be used as a powerful model for prediction of the infinite dilution activity coefficients of halogenated hydrocarbons. Keywords ANFIS CART Infinite dilution activity coefficient Halogenated hydrocarbons
1 Introduction Separation of hazardous chemicals present at very small concentrations from drinking water is one of the significant problems in environmental areas. Also, water is used as the primary solvent for most biochemical recovery processes and thus must perform separations from dilute process streams. Therefore, the thermodynamic behavior of dilute aqueous solutions is crucial for the design of many separation processes and governs how these separation processes can be carried out successfully. The infinite dilution activity coefficients, c?, provide valuable information regarding the solute–solvent interactions. The magnitude of these infinite dilution activity coefficients shows the type and strength of interactions between the solvent and the solute molecules [1, 2]. Activity coefficients at infinite dilution are important for characterizing the behavior of liquid mixtures, predicting the existence of an azeotrope, the estimation of mutual solubilities, providing incisive information for statistical thermodynamics, K. Zarei (&) M. Atabati School of Chemistry, Damghan University, Damghan, Iran e-mail: [email protected]
123
J Solution Chem (2013) 42:516–525
517
analytical chromatography, screening solvents for extraction and extractive distillation processes, the calculation of limiting separation factors necessary for the reliable design of distillation processes, and the calculation of Henry constants and partition coefficients and the development of predictive methods [2–6]. Several methods were developed for the measurement of c?. The most important methods are: gas–liquid chromatography (GLC), non-steady-state gas–liquid chromatography, differential ebulliometry, static methods and the dilutor method [3, 4, 7–10]. In the present work, the prediction of infinite dilution activity c
Data Loading...
