Artificial neural network aided virtual screening of additives to a Co/SrCO 3 catalyst for preferential oxidation of CO in excess hydrogen

Abstract

Preferential oxidation (PROX) of 0.7–1 vol% CO was investigated using the stoichiometric amount of O 2 in excess hydrogen. Cobalt supported on SrCO 3 showed high selectivity to PROX of CO, and the new additive to the Co/SrCO 3 catalyst was investigated for the high tolerance towards CO 2 and H 2O. Representative 10 elements (B, K, Sc, Mn, Zn, Nb, Ag, Nd, Re, and Tl) were selected to represent the physicochemical properties of all elements suitable for additives of solid catalyst. A supported cobalt catalyst with one kind of the above additive was prepared for CO PROX reaction. The activities at 240 °C and the physicochemical properties of the 10 elements were used as training data of a radial basis function network (RBFN), a kind of artificial neural network. After the training, the RBFN predicted the catalytic performance of the supported catalyst containing various element X as Co–X/SrCO 3. The elements such as Bi, Ga, and In were predicted to be promising additives. Finally, the catalytic performance of these additives was experimentally verified. Sixty four percent of CO conversion and 70% selectivity for PROX at 240 °C was achieved in the presence of excess carbon dioxide and steam by Co 3.2–Bi 0.3 mol%/SrCO 3 pretreated at 345 °C.