Scholarlink

<p>In this study, response surface methodology (RSM) and artificial neural networks (ANNs) were used to establish an approach for evaluating heavy metal adsorption processes. Shell powder (CP) was used as an environmentally friendly and economical adsorbent for nickel removal.</p><p>The adsorbent was then characterized by Fourier transform infrared spectroscopy (FTIR). The effect of operational parameters influencing the adsorption capacity of an inorganic pollutant (nickel) by a natural adsorbent (CaCO₃) in the context of aquatic remediation, such as pH, temperature, contact time, initial metal concentration, adsorbent dose, and stirring speed, was investigated using a Box-Behncken design of experiments (BBD). This same design was also used to obtain a training set for the ANN.</p><p>The results showed that the adsorbent (PC) improved the nickel adsorption capacity. Both the RSM and ANN models accurately predicted nickel adsorption, with correlation coefficients of 0.999 and 0.788, respectively. The RSM model proved more accurate, exhibiting the lowest root mean square error (RMSE). An optimal adsorption efficiency of 86.85% was achieved for 2.84&#xa0;g of shell powder (SSP) at pH 5.95, a mass of 2.84&#xa0;g, a temperature of 334&#xa0;K ± 2, a contact time of 79.85&#xa0;min, and a nickel ion concentration of 207.95&#xa0;ppm. Furthermore, FTIR analysis of the shell powder confirmed the presence of broad bands characteristic of the (C = O) group, one at 1631.7&#xa0;cm⁻<sup>1</sup> and the other at 3467.8&#xa0;cm⁻<sup>1</sup>.</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

Response surface methodology and artificial neural network modeling study on optimizing heavy metal adsorption using shell powder

  • 期刊论文

  • 发表日期：

    2026年1月4日

查看全文
  • M. Allaoui,
  • Y. Elrhayam,
  • S. I. Ahmed

摘要

In this study, response surface methodology (RSM) and artificial neural networks (ANNs) were used to establish an approach for evaluating heavy metal adsorption processes. Shell powder (CP) was used as an environmentally friendly and economical adsorbent for nickel removal.

The adsorbent was then characterized by Fourier transform infrared spectroscopy (FTIR). The effect of operational parameters influencing the adsorption capacity of an inorganic pollutant (nickel) by a natural adsorbent (CaCO₃) in the context of aquatic remediation, such as pH, temperature, contact time, initial metal concentration, adsorbent dose, and stirring speed, was investigated using a Box-Behncken design of experiments (BBD). This same design was also used to obtain a training set for the ANN.

The results showed that the adsorbent (PC) improved the nickel adsorption capacity. Both the RSM and ANN models accurately predicted nickel adsorption, with correlation coefficients of 0.999 and 0.788, respectively. The RSM model proved more accurate, exhibiting the lowest root mean square error (RMSE). An optimal adsorption efficiency of 86.85% was achieved for 2.84 g of shell powder (SSP) at pH 5.95, a mass of 2.84 g, a temperature of 334 K ± 2, a contact time of 79.85 min, and a nickel ion concentration of 207.95 ppm. Furthermore, FTIR analysis of the shell powder confirmed the presence of broad bands characteristic of the (C = O) group, one at 1631.7 cm⁻1 and the other at 3467.8 cm⁻1.