Radial Basis Function Neural Network Model Prediction of Thermo-catalytic Carbon Dioxide Oxidative Coupling of Methane to C2-hydrocarbon

Abstract

Various anthropogenic activities often result in the emission of carbon dioxide (CO2), which is one of the principal components of greenhouse gases responsible for greenhouse effect. One vital strategy to mitigate the effect of the released CO2 on the environment is through sustainable utilization and conversion to value-added chemicals. This study employs the Radial Basis Function artificial neural network for modeling the prediction of thermo-catalytic CO2 oxidative coupling of methane to C2-hydrocarbons. The various architecture of the Radial Basis Function ANN was developed, trained, and tested using the non-linear relationship between the input parameters (reaction temperature, amount of CaO and MnO in the CaO-MnO/CeO2 catalysts and the CO2/CH4 ratio) and the output parameters (C2 hydrocarbon selectivity and yield). The Radial Basis Function ANN architecture with the topology of 4-20-2, representing the input layer, hidden neurons, and the output layer offers the best performance with a sum of square error (SSE) of 3.9 × 10−24 for training and 0.224 for testing. The R2 of 0.989 and 0.998 obtained for the prediction of the selectivity and the yield of the C2 hydrocarbon is an indication of the robustness of the Radial Basis Function ANN model. The sensitivity analysis revealed that the input parameters significantly influence the model output. However, the reaction temperature has the most significant influence on the model output based on the level of importance.