Scholarlink

<p>The increasing need for efficient CO<sub>2</sub> capture methods has led to the exploration of NaOH-modified nanoclay montmorillonite as an adsorbent. This study utilizes response surface methodology (RSM) and artificial neural networks (ANN) for modelling and optimizing CO<sub>2</sub> adsorption. Data from previous experiments were used to develop the models. RSM employed a central composite design (CCD) and was evaluated using analysis of variance (ANOVA), while ANN models were created with various training methods (Levenberg–Marquardt, Bayesian regularization, and scaled conjugate gradient). The ANN model using Bayesian regularization (R<sup>2</sup> = 0.98719; MSE = 0.00049) demonstrated the best predictive accuracy. ANOVA revealed that NaOH concentration, pressure, and temperature significantly affected CO<sub>2</sub> adsorption capacity. Sensitivity analysis confirmed NaOH concentration as the most influential variable. Optimization results indicated that maximum CO<sub>2</sub> adsorption (72.873 mg/g) occurs at 35 °C, 9 bar pressure, 5 mol/L acid concentration, and 30% w/w NaOH. This study effectively applies RSM-CCD and ANN models for optimizing CO<sub>2</sub> adsorption with NNM adsorbent.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adsorption of CO2 Using NaOH-Modified Nanoclay Montmorillonite Adsorbent: Comparative Analysis of RSM-Based Central Composite Design and ANN-Based Models in Modelling and Optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月8日

查看全文
  • Irvan Dahlan,
  • Mahfuzah Hanisah Mohd Suhaimi

摘要

The increasing need for efficient CO2 capture methods has led to the exploration of NaOH-modified nanoclay montmorillonite as an adsorbent. This study utilizes response surface methodology (RSM) and artificial neural networks (ANN) for modelling and optimizing CO2 adsorption. Data from previous experiments were used to develop the models. RSM employed a central composite design (CCD) and was evaluated using analysis of variance (ANOVA), while ANN models were created with various training methods (Levenberg–Marquardt, Bayesian regularization, and scaled conjugate gradient). The ANN model using Bayesian regularization (R2 = 0.98719; MSE = 0.00049) demonstrated the best predictive accuracy. ANOVA revealed that NaOH concentration, pressure, and temperature significantly affected CO2 adsorption capacity. Sensitivity analysis confirmed NaOH concentration as the most influential variable. Optimization results indicated that maximum CO2 adsorption (72.873 mg/g) occurs at 35 °C, 9 bar pressure, 5 mol/L acid concentration, and 30% w/w NaOH. This study effectively applies RSM-CCD and ANN models for optimizing CO2 adsorption with NNM adsorbent.