Reforming of Methane in a Plasma Reactor: Prediction of Conversion with Artificial Neural Network Technique

Performance of the dry reforming of methane (DRM) at atmospheric pressures and low temperatures has been simulated by a set of supervised a three-layer back-propagation Artificial Neural Network (ANN) models using reaction data gathered in a corona discharge microreactor device.The effect of discharge power and gas flow rate on the reaction performance of the plasma methane conversion and the selectivity of gas products are investigated. A good agreement between the experimental and simulated results is achieved. The ANN model predicted the methane conversion of 56.7% and selectivity of H2 66.02%, can be obtained at a discharge power of 8 W. The results successfully demonstrate that the well-trained ANN model can accurately simulate and predict a complex plasma chemical reaction.

کلیدواژه ها:

Reforming ، Methane ، Plasma reactor ، Artificial Neural Network (ANN)