Modeling of Ni(II) Separation from Aqueous Solutions onto Aspergillus awamori using Artificial Neural Technique

This study presents the application of artificial neural network (ANN) for modeling the Nickel(II) biosorption from aqueous solutions onto Aspergillus awamori. The effect of operational parameters such as initial pH, adsorbent dosage, contact time, and initial concentration of Ni(II) ions were studied to optimize the conditions for maximum removal of Ni(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 6.0, an adsorbent dosage of 0.25g, an initial Ni(II) concentration of 25 ppm, and a contact time of 180 min. A three layer feed forward neural network with back propagation (BP) training algorithm was developed using 140 experimental data obtained from a batch laboratory study. The ANN model was able to predict separation efficiency with a tan-sigmoid transfer function at hidden layer with 9 neurons and a linear purelin function at output layer. The Levenberg–marquardt algorithm (LMA) was found as the best algorithms with smallest mean squared error (MSE). The linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.962 for model used in this research. Further more, the ANN predicted results were compared with the experimental results of the laboratory tests and the accuracy of the ANN model was evaluated.

Keywords:

Artificial neural networks , FF-ANN , Modeling , Nickel (II) , Biosorption