Investigation of toluene oxidation activity of Perovskite-Type La-Sr-Ce-Cu-MnO3 Nano catalyst using artificial neural networks

The toluene oxidation activities of La-Sr-Ce-Cu-MnO3 Perovskite-Type catalysts were investigated in this work. The catalysts were prepared by sol-gel combustion method and tested using a microflow reaction system. It was found that the catalytic activity increases with the degree of substitution of La by Ce and Sr. the experimental results were also modeled using an artificial neural network, at which the catalyst preparation and operational (reaction temperature) variables were used together in the same network. Based on results, the best structure for feed-forward back propagation neural network is Levenberg-Marquardt back propagation training algorithm, hyperbolic tangent sigmoid transformation function for hidden layer and linear transformation function for output layer. The multiplayer network model with 12 neurons in the hidden layer has the least AAD% for prediction of toluene oxidation. Results show that best neural network architecture is able to predict toluene oxidation with an acceptable level of accuracy

Keywords:

Artificial neural network , Toluene oxidation , Perovskite catalysts , sol-gel combustion method