Prediction of Density of Binary Mixtures of Ionic Liquids with Alcohols (Methanol/Ethanol/1-Propanol) using Artificial Neural Network
| Autor: | Karen Faith P. Ornedo Ramos, Allan N. Soriano, Vergel C. Bungay, Carla Angela M. Muriel, Adonis P. Adornado |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Zdroj: | ASEAN Journal of Chemical Engineering; Vol 16, No 2 (2016); 33-50 ASEAN Journal of Chemical Engineering; Vol 15, No 2 (2015); 33-50 |
| ISSN: | 1655-4418 2655-5409 |
| Popis: | Ionic liquids demonstrated successful potential applications in the industry most specifically as the new generation of solvents for catalysis and synthesis in chemical processes, thus knowledge of their physico-chemical properties is of great advantage. The present work presents a mathematical correlation that predicts density of binary mixtures of ionic liquids with various alcohols (ethanol/methanol/1-propanol). The artificial neural network algorithm was used to predict these properties based on the variations in temperature, mole fraction, number of carbon atoms in the cation, number of atoms in the anion, number of hydrogen atoms in the anion and number of carbon atoms in the alcohol. The data used for the calculations were taken from ILThermo Database. Total experimental data points of 1946 for the considered binaries were used to train the algorithm and to test the network obtained. The best neural network architecture determined was found to be 6-6-10-1 with a mean absolute error of 48.74 kg/m3. The resulting correlation satisfactorily represents the considered binary systems and can be used accurately for solvent related calculations requiring properties of these systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|