中国科学院过程工程研究所机构知识库

A hybrid methodology of using lump kinetic and of AANs (Artificial Neuron Networks)/RSM (Response Surface Methodology) was investigated for modeling Fischer-Tropsch (FT) synthesis in a microchannel reactor using iron-based catalyst in this work. This robust and cost-effective methodology was reliable to extensively analyze the effect of operating conditions including TOS (time on stream), partial pressures of different gases in reaction system (H-2, CO, CO2 and H2O) on CO disappearance rate. With experimental data as training data set using ANNs and Box-Behnken design as design of experiment, the setup model was able to present good results in nonlinear noisy processes with significant changes of operational parameters in experimental design plan. The proposed hybrid methodology was able to provide comprehensive information such as reaction mechanism, the multiple combined effects on the studied response, and significance of process parameters during FT synthesis using iron-based catalyst in microchannel reactor.