Employing an Artificial Neural Network in Correlating a Hydrogen-Selective Catalytic Reduction Performance with Crystallite Sizes of a Biomass-Derived Bimetallic Catalyst

A predictive model correlating the properties of a catalyst with its performance would be beneficial for development, from biomass waste, new, carbon-supported and Earth-abundant metal oxide catalysts. In this work, effects copper iron crystallite size on catalysts in reducing nitrogen oxides, terms conversion selectivity, are investigated. The prepared via incipient wetness method over activated carbon, derived palm kernel shells. surface morphology particle distribution examined field emission scanning electron microscopy, while is determined using wide-angle X-ray scattering small-angle methods. It revealed that copper-to-iron ratio affects crystal phases carbon support. Catalytic then tested packed-bed reactor to investigate selectivity. Departing chemical characterization, two equations developed an artificial neural network technique—one prediction NOx another N2 highly applicable 250–300 °C operating temperatures, more data required lower temperature range.