مليكا عربي

Adsorption of CO₂ on porous carbon materials is an effective an‎d cost-efficient method to reduce the emission of this gas. One promising approach for modeling CO₂ adsorption is the use of machine learning techniques, which, with their high capability in predicting nonlinear behaviors, can accurately estimate the CO₂ uptake by solid adsorbents. In this study, the effects of independent parameters such as specific surface area, micropore an‎d mesopore volume, as well as operational conditions including temperature, pressure, an‎d time on CO₂ adsorption capacity were investigated. For process modeling, machine learning methods an‎d artificial neural networks (ANNs) were employed. Two types of neural networks, multilayer perceptron (MLP) an‎d radial basis function (RBF), along with response surface methodology (RSM), were utilized, an‎d the required data were extracted from literature sources. The dataset was ran‎domly divided into training (70%), validation (15%), an‎d testing (15%) subsets to accurately assess model performance. Initially, RSM was applied to eva‎luate interaction effects among variables an‎d optimize adsorption conditions. Results indicated that specific surface area, micropore volume, an‎d pressure significantly influenced adsorption capacity, an‎d the optimum conditions for maximum CO₂ uptake were determined. The RSM model achieved a correlation coefficient of 0.9299, indicating good accuracy. In the simulation phase, the MLP architecture was tested with three backpropagation learning algorithms, an‎d their performance was compared in terms of accuracy, computational speed, an‎d processing cost. The Levenberg–Marquardt (LM) an‎d Bayesian Regularization (BR) algorithms outperformed the Scaled Conjugate Gradient (SCG) algorithm, with BR achieving a minimum mean squared error (MSE) of 0.0005411 an‎d a correlation coefficient of 0.9912, whereas SCG showed the lowest accuracy. Regarding the RBF network, the optimal structure consisted of 327 neurons in the hidden layer an‎d a spread parameter of 0.01, with an MSE of 1.08691e-05. Overall, RBF exhibited higher accuracy compared to MLP. To eva‎luate model generalization, both networks were tested on 50 new data points, confirming that MLP with BR an‎d RBF with 0.01 spread provided the highest accuracy. Finally, analysis revealed that at low pressures, CO₂ adsorption is more influenced by micropore volume, while at higher pressures, mesopore volume plays a more significant role. Additionally, specific surface area has a substantial effect on the overall adsorption capacity.

جذب سطحي , جاذب , شبكه¬هاي عصبي , الگوريتم , CO2

adsorption , Adsorbent , Neural Networks , algorithm , CO2

Melaka Arabi

Dr, Ghaemi