Artificial neural network model of catalytic coal gasification in fixed bed

Abstract

Catalytic coal gasification is a cost-effective way to utilize coal to produce hydrogen or methane. Because of complex interactions among hydrodynamics and chemical reactions with catalyst, it was very difficult to predict hydrogen yield and carbon conversion. Therefore, three kinds of artificial neural network (ANN) models, including feed-forward back propagation neural network (FFBP), cascade-forward back propagation neural network with Levenberge Marquardt algorithms (CFBP), and cascade-forward back propagation neural network with genetic algorithm (CFBP-GA) were used to predict these processes. Three kinds of input parameters were used, such as coal ultimate analyses, coal proximate analyses and operation conditions. Gas yield and carbon conversion were taken as output parameters. R2 of all three established ANN models were above 0.9. The CFBP-GA showed good performance with E2 = 0.000241 and R2 = 0.9978 than the other two ANN models. And then, the model was used to predict the effects of temperature, catalyst type and catalyst loading on carbon conversion and hydrogen yield. The most important three factors for carbon conversion and hydrogen yield were catalyst type, catalyst loading and temperature based on relative importance analysis. The good performances were indicated the ANN model was an effective way to predict hydrogen production and carbon conversion of catalytic coal gasification in fixed bed quickly and accurately, and it could be also extended to other carbon resources to produce hydrogen.