What is it about?
The adsorption process is affected by multiple parameters thus require an efficient solution to establish a significant correlation. In this work, we demonstrated for the first time the combination of an Artificial Neural Network (ANN) with the Monte Carlo (MC) technique to predict the nonlinear correlation of different parameters for Pb (II) removal via adsorption by multi-walled carbon nanotubes (MWCNTs). The hybrid ANN-MC approach will improve the network efficiency by demonstrating the effects of the important variables and showing the effects of the other affecting variables.
Featured Image
Photo by DeepMind on Unsplash
Why is it important?
The trained network was used to analyze the influence of input parameters by constructing three-dimensional (3D) plots and contour graphs. The parameters analysis revealed that the Pb (II) ions removal from the wastewater was significantly influenced by the combination of pH and MWCNTs dose as compared to other parameters. Through the coupling of ANN models with the Monte Carlo technique, the maximum Pb (II) ion removal efficiency of 99.82% was achieved at optimum conditions: pH, dosage, contact time, and concentration of pollutant of 10, 0.05 g, 60 min, and 100 mg/L, respectively.
Perspectives
This article focused on the solid-liquid interaction predicted via hybrid ANN-MC and validated experimentally.
Dr. Thaer Al-Jadir
University of Technology- Iraq
Read the Original
This page is a summary of: Modeling of lead (II) ion adsorption on multiwall carbon nanotubes using artificial neural network and Monte Carlo technique, Chemical Engineering Communications, October 2022, Taylor & Francis,
DOI: 10.1080/00986445.2022.2129622.
You can read the full text:
Contributors
The following have contributed to this page
