Skip to main content

Prediction of adsorption efficiency for the removal malachite green and acid blue 161 dyes by marble sludge dust using ANN

  • Authors (legacy)
    Corresponding: semra çoruh
    Co-authors: Coruh, S
    Gürkan, E.H.
    Kılıç, E.
    Geyikci, F.
    Download PDF
  • gnest_01366_published.pdf
  • Paper ID
    gnest_01366
  • Paper status
    Published
  • Date paper accepted
  • Date paper online
Abstract

In the present study, batch adsorption studies were performed for the removal of malachite green and acid blue 161 dyes from aqueous solutions by varying parameters such as contact time, waste marble dust amount, initial dye concentration and temperature. The equilibrium adsorption data were analyzed by Langmuir, Freundlich and Temkin adsorption isotherm models. The Langmuir and Freundlich adsorption models agree well with experimental data. The pseudo-second order, intraparticle intraparticle diffusion and Elovich kinetic models were applied to the experimental data in order to describe the removal mechanism of dye ions by waste marble dust. The pseudo-second order kinetic was the best fit kinetic model for the experimental data. Thermodynamics parameters such as ΔG, ΔH and ΔS were also calculated for the adsorption processes. The experimental data were used to construct an artificial neural network (ANN) model to predict removal of malachite green and acid blue 161 dyes by waste marble dust. A three-layer ANN, an input layer with four neurons, a hidden layer with 12 neurons, and an output layer with one neuron is constructed. Different training algorithms were tested on the model to obtain the proper weights and bias values for ANN model. The results show that waste marble dust is an efficient sorbent for malachite green dye and ANN network, which is easy to implement and is able to model the batch experimental system.

 

Copy to clipboard
Cite this article
?oruh, semra (2014) “Prediction of adsorption efficiency for the removal malachite green and acid blue 161 dyes by marble sludge dust using ANN”, Global NEST Journal, 16(4). Available at: https://doi.org/10.30955/gnj.001366.