pouya Es'haghi; Alireza Mohammadi; Keivan Shayesteh; Hassan Seddighi
Abstract
Ethanol (EtOH) purification is a pivotal research pursuit, with liquid-liquid extraction emerging as a significant purification methodology. This study focuses on utilizing benzene solvent for EtOH purification and investigates the liquid-liquid equilibrium (LLE) within three-component systems comprising ...
Read More
Ethanol (EtOH) purification is a pivotal research pursuit, with liquid-liquid extraction emerging as a significant purification methodology. This study focuses on utilizing benzene solvent for EtOH purification and investigates the liquid-liquid equilibrium (LLE) within three-component systems comprising EtOH, water, and benzene. Thermodynamic modeling of EtOH-benzene-water systems at temperatures of 20 °C, 30 °C, 40 °C, and 55 °C was conducted. In this paper, the equations used for predicting mole fraction include Non-Random Two-Liquid (NRTL), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Multilayer Perceptron Artificial Neural Network (MLP-ANN). First, the equation parameters were optimized using the particle swarm optimization (PSO) algorithm to employ the NRTL equation Experimental data was used to train the MLP-ANN and ANFIS methods, and the same experimental datasets were used for all models. These models estimated integral components across both phases, revealing effective system control across all methodologies. However, the comparative analysis indicated the superior performance of the MLP-ANN and ANFIS methods over the NRTL model. The Root Mean Square Deviation (RMSD) errors for the NRTL, MLP-ANN, and ANFIS models were 0.0253, 0.0035, and 0.0017, respectively. These results indicate that despite the low prediction error of all three methods, the NRTL equation has the highest error, and the ANFIS method has the lowest mole fraction prediction error.
Sayyed Hossein Hashemi; Massoud Kaykhaii; Mohamad Shakeri
Abstract
In this research, a new modeling method based on three-layer artificial neural network (ANN) technique was applied to predict the extraction yield of copper-morin complex from aqueous samples by means of molecularly imprinted stir bar sorptive extraction. Input variables of the model were pH of the solution, ...
Read More
In this research, a new modeling method based on three-layer artificial neural network (ANN) technique was applied to predict the extraction yield of copper-morin complex from aqueous samples by means of molecularly imprinted stir bar sorptive extraction. Input variables of the model were pH of the solution, absorption and desorption times, stirring rate, temperature, and amount of morin ligand; while the output was extraction yield of copper ions. It was found that a network with 12 hidden neurons is highly accurate in predicting extraction recovery of copper-morin complex. The mean squared error and correlation coefficient between the experimental data and the ANN predictions were achieved as 0.0009 and 0.9999 for training, 0.0032 and 0.976 for validation and 0.0030 and 0.96666 for testing data sets. Under the optimum conditions, the linear range found to be in the range of 5-1000 μg L-1 with the detection limit of 0.38 μg L-1. The relative standard deviation was obtained to be below 5.3%. The method was successfully applied for preconcentration and determination of Cu in a few real samples.
