Evaluation of hydrogen production via steam reforming and partial oxidation of dimethyl ether using response surface methodology and artificial neural network.

This study aims to develop two models for thermodynamic data on hydrogen generation from the combined processes of dimethyl ether steam reforming and partial oxidation, applying artificial neural networks (ANN) and response surface methodology (RSM). Three factors are recognized as important determinants for the hydrogen and carbon monoxide mole fractions. The RSM used the quadratic model to formulate two correlations for the outcomes. The ANN modeling used two algorithms, namely multilayer perceptron (MLP) and radial basis function (RBF). The optimum configuration for the MLP, employing the Levenberg-Marquardt (trainlm) algorithm, consisted of three hidden layers with 15, 10, and 5 neurons, respectively. The ideal RBF configuration contained a total of 80 neurons. The optimum configuration of ANN achieved the best mean squared error (MSE) performance of 3.95e-05 for the hydrogen mole fraction and 4.88e-05 for the carbon monoxide mole fraction after nine epochs. Each of the ANN and RSM models produced accurate predictions of the actual data. The prediction performance of the ANN model was 0.9994, which is higher than the RSM model's 0.9771. The optimal condition was obtained at O/C of 0.4, S/C of 2.5, and temperature of 250 °C to achieve the highest H2 production with the lowest CO emission.

Experimental, RSM modelling, and DFT simulation of CO2 adsorption on Modified activated carbon with LiOH.

This research investigates the enhancement of CO2 adsorption capacity through the use of modified activated carbon (AC) with LiOH, focusing on operational conditions and adsorbent properties. Response Surface Methodology (RSM) is employed to optimize process parameters for maximizing CO2 adsorption capacity. The study considers temperature, pressure, LiOH concentration for modification, and adsorbent weight as independent variables across five levels. Analysis of Variance reveals that LiOH concentration, adsorbent quantity, pressure, and temperature significantly influence CO2 adsorption. Optimal values for temperature (30°C), pressure (9 bar), LiOH concentration (0.5 mol/L), and adsorbent weight (0.5 g) result in a maximal CO2 adsorption capacity of 154.90 mg/g. Equilibrium adsorption capacity is utilized for modeling, with the Freundlich model proving suitable for CO2 adsorption on LiOH-AC. Kinetic modeling indicates the second-order model's suitability for temperatures of 30 °C and 50 °C, while the Elovich model fits temperatures of 70 °C and 90 °C. Thermodynamic modeling at the optimized conditions (303 K and 6 bar) yields ∆H, ∆S, and ∆G values of adsorption as 12.258 kJ/mol, - 0.017 kJ/mol·K, and - 7.031 kJ/mol, respectively. Furthermore, structural considerations of AC are discussed alongside modeling and simulation, presenting the adsorption rate of CO2 and the binding energy index based on Density Functional Theory (DFT).

Modeling based on machine learning to investigate flue gas desulfurization performance by calcium silicate absorbent in a sand bed reactor.

Flue gas desulfurization (FGD) is a critical process for reducing sulfur dioxide (SO2) emissions from industrial sources, particularly power plants. This research uses calcium silicate absorbent in combination with machine learning (ML) to predict SO2 concentration within an FGD process. The collected dataset encompasses four input parameters, specifically relative humidity, absorbent weight, temperature, and time, and incorporates one output parameter, which pertains to the concentration of SO2. Six ML models were developed to estimate the output parameters. Statistical metrics such as the coefficient of determination (R2) and mean squared error (MSE) were employed to identify the most suitable model and assess its fitting effectiveness. The random forest (RF) model emerged as the top-performing model, boasting an R2 of 0.9902 and an MSE of 0.0008. The model's predictions aligned closely with experimental results, confirming its high accuracy. The most suitable hyperparameter values for RF model were found to be 74 for n_estimators, 41 for max_depth, false for bootstrap, sqrt for max_features, 1 for min_samples_leaf, absolute_error for criterion, and 3 for min_samples_split. Three-dimensional surface plots were generated to explore the impact of input variables on SO2 concentration. Global sensitivity analysis (GSA) revealed absorbent weight and time significantly influence SO2 concentration. The integration of ML into FGD modeling offers a novel approach to optimizing the efficiency and effectiveness of this environmentally crucial process.

Improving the efficiency of 4A-zeolite synthesized from kaolin by amine functionalization for CO2 capture.

This study focuses on optimizing the CO2 adsorption capacity of 4A-zeolite synthesized from kaolin by employing structural modifications through impregnation with tetraethylenepentamine (TEPA) and diethanolamine (DEA). Various analytical techniques were utilized to evaluate the effectiveness of these modifications. Design expert software and response surface methodology (RSM) was employed for data analysis and operational variable optimization, leading to improved CO2 adsorption performance of the modified zeolites. The adsorption capacity of the modified zeolites was assessed under different temperatures, pressures, and amine concentrations using a test device. The optimal adsorption capacity of 4A-DEA adsorbent is found to be 579.468 mg/g, with the optimal operational variables including a temperature of 25.270 °C, pressure of 8.870 bar, and amine concentration of 11.112 wt%. The analysis shows that the adsorption process involves both physisorption and chemisorption, and the best kinetic model is the fractional-factor model.