Growth of MWCNTs from Azadirachta indica oil for optimization of chromium(VI) removal efficiency using machine learning approach.

Abstract

The main objective of the present study is to develop artificial neural networks (ANN) to predict the adsorption efficiency of multi-walled carbon nanotubes (MWCNTs) on Cr(VI) removal. Polydisperse MWCNTs were synthesized at 750°C on alumina supported Fe-Co-Mo catalyst using CVD (chemical vapor deposition)-assisted spray pyrolysis of Azadirachta indica (Neem) oil under inert Argon (Ar) atmosphere. Growth of MCWNTs with inner diameters between 9 and 14nm was corroborated by scanning electron microscopy (SEM), high resolution transmission electron microscopy (HRTEM), X-ray diffraction analysis (XRD), and Raman spectral evidence assessments. The metal-ion adsorbent capacity (Cr-VI) of the as such prepared MWCNTs was examined for industrial purposes. Different parameters such as adsorption isotherms, kinetics, and thermodynamic parameters were analyzed for the removal of metal ions with MWCNTs. The results of isotherm, kinetic, and thermodynamic study indicated that the process suited well with Langmuir isotherm, pseudo second-order kinetics, and followed endothermic reaction, respectively. The effects of parameters such as adsorbent dosage, concentration of chromium ion (Cr-VI), pH, and contact time were studied to optimize the maximum removal of Cr(VI). In order to optimize the process conditionsusing Artificial Neural Networks, Box-Behnken design (BBD)was used to design the batch adsorption experiments, and the resulting datasets were used as the input for ANN. To predict the adsorption efficiency, various ANN architectures were examined using different training algorithms, number of neurons in the hidden layer, and the transfer function for the hidden and output layers. A neural network structure with Levenberg-Marquardt (LM) training algorithm, 14 hidden neurons, and tangent sigmoid transfer function at the hidden layer and logarithmic sigmoid transfer function at the output layer furnished the best level of prediction results. Comparing with experimental data, the optimal model capitulated mean square error (MSE),and correlation coefficient (R2) of 0.0324 and 0.99512, respectively. The results showed that ANN is well-organized in predicting the adsorption efficiency of MWCNTs for Cr(VI) metal ion removal process.