Development of novel computational models based on artificial intelligence technique to predict liquids mixtures separation via vacuum membrane distillation

The fundamental objective of this paper is to use Machine Learning (ML) methods for building models on temperature (T) prediction using input features r and z for a membrane separation process. A hybrid model was developed based on computational fluid dynamics (CFD) to simulate the separation process and integrate the results into machine learning models. The CFD simulations were performed to estimate temperature distribution in a vacuum membrane distillation (VMD) process for separation of liquid mixtures. The evaluated ML models include Support Vector Machine (SVM), Elastic Net Regression (ENR), Extremely Randomized Trees (ERT), and Bayesian Ridge Regression (BRR). Performance was improved using Differential Evolution (DE) for hyper-parameter tuning, and model validation was performed using Monte Carlo Cross-Validation. The results clearly indicated the models' effectiveness in temperature prediction, with SVM outperforming other models in terms of accuracy. The SVM model had a mean R2 value of 0.9969 and a standard deviation of 0.0001, indicating a strong and consistent fit to the membrane data. Furthermore, it exhibited the lowest mean squared error, mean absolute error, and mean absolute percentage error, signifying superior predictive accuracy and reliability. These outcomes highlight the importance of selecting a suitable model and optimizing hyperparameters to guarantee accurate predictions in ML tasks. It demonstrates that using SVM, optimized with DE improves accuracy and consistency for this specific predictive task in membrane separation context.

Intelligence analysis of membrane distillation via machine learning models for pharmaceutical separation

This study investigates simulation of pharmaceutical separation via membrane distillation process by computational simulation and machine learning modeling strategy. The efficacy of three regression models, i.e., Multi-layer Perceptron (MLP), Gamma Regression, and Support Vector Regression (SVR) in predicting the solute concentration, C(mol/m³), was evaluated. The hyper-parameters were optimized by fine-tuning the models using the Red Deer Algorithm (RDA). Computational analyses were carried out for removal of pharmaceuticals from solution by membrane distillation in continuous mode. Mass transfer and machine learning models were implemented focusing on concentration of solute in the feed section of membrane. Results indicate that the Multi-layer Perceptron model achieved great accuracy with an R2 of 0.9955, an MAE of 0.0084, and an RMSE of 0.0148, effectively capturing complex nonlinear relationships in the data. Gamma Regression also performed acceptably, with fitting R2 of 0.9214, showing its suitability for positively skewed data. The Support Vector Regression model, while capturing the general trend, showed the lowest performance with an R2 of 0.8710. These findings suggest that the Multi-layer Perceptron is the most accurate model for this dataset, followed by Gamma Regression and Support Vector Regression. This underscores the importance of careful model selection and optimization in regression analysis in combination with computational simulation of membrane processes.

Modeling and validation of purification of pharmaceutical compounds via hybrid processing of vacuum membrane distillation

This study provides an in-depth examination of forecasting the concentration of pharmaceutical compounds utilizing the input features (coordinates) r and z through a range of machine learning models. Purification of pharmaceuticals via vacuum membrane distillation process was carried out and the model was developed for prediction of separation efficiency based on hybrid approach. Dataset was collected from mass transfer analysis of process to obtain concentration distribution in the feed side of membrane distillation and used it for machine learning models. The dataset has undergone preprocessing, which includes outlier detection using the Isolation Forest algorithm. Three regression models were used including polynomial regression (PR), k-nearest neighbors (KNN), and Tweedie regression (TWR). These models were further enhanced using the Bagging ensemble technique to improve prediction accuracy and reduce variance. Hyper-parameter optimization was conducted using the Multi-Verse Optimizer algorithm, which draws inspiration from cosmological concepts. The Bagging-KNN model had the highest predictive accuracy (R2 = 0.99923) on the test set, indicating exceptional precision. The Bagging-PR model displayed satisfactory performance, with a slightly reduced level of accuracy. In contrast, the Bagging-TWR model showcased the least accuracy among the three models. This research illustrates the effectiveness of incorporating bagging and advanced optimization methods for precise and dependable predictive modeling in complex datasets.

Improved water purification by PVDF ultrafiltration membrane modified with GO-PVA-NaAlg hydrogel

This work presents a modified polyvinylidene fluoride (PVDF) ultrafiltration membrane blended with graphene oxide-polyvinyl alcohol-sodium alginate (GO-PVA-NaAlg) hydrogel (HG) and polyvinylpyrrolidone (PVP) prepared by the immersion precipitation induced phase inversion approach. Characteristics of the membranes with different HG and PVP concentrations were analyzed by field emission scanning electron microscopy (FESEM), Atomic force microscopy (AFM), contact angle measurement (CA), and Attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR). The FESEM images showed an asymmetric structure of the fabricated membranes, and possessing a thin dense layer over the top and a layer finger-like. With increasing HG content, membrane surface roughness increases so that highest surface roughness for the membrane containing 1wt% HG is with a Ra value of 281.4 nm. Also, the contact angle of the membrane reaches from 82.5° in bare PVDF membrane to 65.1° in the membrane containing 1wt% HG. The influences of adding HG and PVP to the casting solution on pure water flux (PWF), hydrophilicity, anti-fouling ability, and dye rejection efficiency were evaluated. The highest water flux reached 103.2 L/m² h at 3 bar for the modified PVDF membranes containing 0.3 wt% HG and 1.0wt% PVP. This membrane exhibited a rejection efficiency of higher than 92%, 95%, and 98% for Methyl Orange (MO), Conge Red (CR), and Bovine Serum Albumin (BSA), respectively. All nanocomposite membranes possessed a flux recovery ratio (FRR) higher than bare PVDF membranes, and the best anti-fouling performance of 90.1% was relevant to the membrane containing 0.3 wt% HG. The improved filtration performance of the HG-modified membranes was due to the enhanced hydrophilicity, porosity, mean pore size, and surface roughness after introducing HG.

Computational simulation and modelling of uranium extraction using tributylphosphate through membrane extractor

Non-disperse solvent extraction is an effective technique for the extraction of metal ions from aqueous solution. In this study, uranium extraction using n-dodecane solvent containing tributylphosphate extractant in a membrane contactor was investigated. A 2D mathematical model was developed for the fluid flow and mass transfer in the hollow fibre membrane extractor. The equations of the created model were solved using the finite element method. The uranium concentration distribution in the extractor at different extractant concentrations as well as feed acidity was studied. The results showed that there is reasonable good agreement between experimental uranium extraction and modelling outputs at different extractant concentrations. Increasing extractant concentration from 5 to 30% led to the enhancement of uranium extraction from 2.60 to 34.13%. Also, there was an increase in the uranium extraction with increasing feed acidity in the range of 1–3 M. Furthermore, based on the radial uranium concentration distribution, it was found that the main mass transfer resistance in the system was microporous membrane section. Finally, it was obtained that the uranium extraction efficiency could be improved significantly by increasing porosity-to-tortuosity ratio. It was concluded that the membrane specification plays the most important role as the dominant mass transfer resistant was in the membrane subdomain.

Numerical simulation of reactive extraction of benzoic acid from wastewater via membrane contactors

Membrane-based non-dispersive solvent extraction is used in many chemical processes due to its significant benefits such as straightforward scale-up and low energy consumption. A mechanistic model was developed to predict recovery of benzoic acid (BA) from wastewater using membrane contactors. Model equations were derived for benzoic acid transport in the membrane module, and solved using FEM. The model findings were compared with experimental results, and an average deviation of 4% was observed between experimental and simulation results. Simulations showed that change in organic phase flowrate and initial concentration of BA does not have considerable effect on the removal efficiency of benzoic acid. In addition, increasing feed flowrate leads to the enhancement of convective mass transfer flux in the tube side of membrane contactor which decreases removal efficiency of benzoic acid.

Synthesis and characterization of polyurethane/poly(vinylpyridine) composite membranes for desulfurization of gasoline

Polyurethane/poly(vinylpyridine) (PU/PVP) composite membranes for desulfurizing gasoline were prepared.