The use of artificial neural network (ANN) for modeling of COD removal from antibiotic aqueous solution by the Fenton process

J Hazard Mater. 2010 Jul 15;179(1-3):127-34. doi: 10.1016/j.jhazmat.2010.02.068. Epub 2010 Mar 1.

Abstract

The study examined the implementation of artificial neural network (ANN) for the prediction and simulation of antibiotic degradation in aqueous solution by the Fenton process. A three-layer backpropagation neural network was optimized to predict and simulate the degradation of amoxicillin, ampicillin and cloxacillin in aqueous solution in terms of COD removal. The configuration of the backpropagation neural network giving the smallest mean square error (MSE) was three-layer ANN with tangent sigmoid transfer function (tansig) at hidden layer with 14 neurons, linear transfer function (purelin) at output layer and Levenberg-Marquardt backpropagation training algorithm (LMA). ANN predicted results are very close to the experimental results with correlation coefficient (R(2)) of 0.997 and MSE 0.000376. The sensitivity analysis showed that all studied variables (reaction time, H(2)O(2)/COD molar ratio, H(2)O(2)/Fe(2+) molar ratio, pH and antibiotics concentration) have strong effect on antibiotic degradation in terms of COD removal. In addition, H(2)O(2)/Fe(2+) molar ratio is the most influential parameter with relative importance of 25.8%. The results showed that neural network modeling could effectively predict and simulate the behavior of the Fenton process.

MeSH terms

  • Algorithms
  • Anti-Bacterial Agents / isolation & purification*
  • Artificial Intelligence
  • Hydrogen Peroxide / chemistry*
  • Hydrogen-Ion Concentration
  • Iron / chemistry*
  • Models, Chemical
  • Models, Statistical
  • Neural Networks, Computer
  • Neurons
  • Oxygen / analysis*
  • Reproducibility of Results
  • Solutions
  • Water

Substances

  • Anti-Bacterial Agents
  • Fenton's reagent
  • Solutions
  • Water
  • Hydrogen Peroxide
  • Iron
  • Oxygen