Electrochemical promoted dry methane reforming for power and syngas co-generation in solid oxide fuel cells: Experiments, modelling and optimizations

The solid oxide fuel cell (SOFC) combining dry methane reforming (DMR) is an efficient electrochemical power generation device that simultaneously converts greenhouse gases (methane and CO2) into syngas and produces electricity power. The electrochemical promotion of catalysis effect (EPOC) in SOFC is known to be promising for enhancing the syngas conversion e.g. dry methane reforming reaction upon application of electrical currents or potentials. However, traditional DMR catalytic kinetic models were developed from heterogeneous catalysis experimental data, neglecting the EPOC effect and thus fail to accurately predict the DMR catalytic kinetics in SOFC. This study experimentally investigated the EPOC effect on the DMR reaction during SOFC operation, and proposes a machine learning-based predictive model using multiswarm particle swarm optimization algorithm (MSPSO) and back propagating (BP) neural network for the accurate prediction of catalysis performance in DMRSOFCs under the EPOC. Key parameters including molar flow rate, reaction temperature, and electrical potentials are used as input parameters and CH4/CO2 conversion as output in the predictive model. The MSPSO-BP model exhibits high prediction accuracy with the average error of predicted CH4/CO2 conversion less than 5 %, and the coefficient of determination (R2) values are 0.971 and 0.968. respectively. Sensitivity analysis through the response surface method (RSM) reveals that temperature and electrical potentials are the most important parameters affecting dry methane reforming performance under EPOC. The developed model in this work is the first machine learning-based predictive model for DMR-SOFCs with a focus on EPOC effect and co-generation performance, providing a valuable tool for the optimization and design of future efficient DMR-SOFCs systems.