Modeling of electrodialysis using neural network

  • Authors:

  • Mohtada Sadrzadeh;Toraj Mohammadi;Javad Ivakpour;Norollah Kasiri

  • Affiliations:

  • Research Lab for Separation Processes, Department of Chemical Engineering, Iran University of Science and Technology, Narmak, Tehran, Iran;Research Lab for Separation Processes, Department of Chemical Engineering, Iran University of Science and Technology, Narmak, Tehran, Iran;Computer Aided Process Engineering Lab, Department of Chemical Engineering, Iran University of Science and Technology, Narmak, Tehran, Iran;Computer Aided Process Engineering Lab, Department of Chemical Engineering, Iran University of Science and Technology, Narmak, Tehran, Iran

  • Venue:
  • COMPUCHER'07 Proceedings of the 1st WSEAS International Conference on Computational Chemistry
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, separation of lead ions with the aid of a laboratory scale electrodialysis (ED) cell was modeled using artificial neural network (ANN) technique. Separation percent (SP) of lead ions was predicted at various concentrations (100, 500, and 1000 ppm), temperatures (25, 40, and 60°C), flow rates (0.07, 0.7, and 1.2 mL/s) and voltages (10, 20, and 30 V). An ANN structure with two hidden layers (4:5:4:1) was used for prediction. The modeling results showed that there is an excellent agreement between the experimental data and the predicted values, with mean absolute errors less than 1%. ANN modeling technique was found out to have many favorable features such as efficiency, generalization and simplicity, which make it an attractive choice for modeling of complex systems, such as wastewater treatment processes.