A review of hydrogen production optimization from the reforming of C1 and C2 alcohols via artificial neural networks

Hydrogen production from different fuels has received extensive study interest owing to its environmental sustainability, renewability, and lack of carbon emission. This research aims to investigate how artificial neural networks (ANNs) are employed to optimize operating parameters for the catalytic thermochemical conversion of methanol and ethanol and their impact on hydrogen production. According to the ANN model, peak methanol conversion (99%) occurs at lower temperatures of 300 °C with a maximum hydrogen yield of 2.905 mol, whereas peak ethanol conversion (85%) occurs at 500 °C owing to dehydrogenation and the C-C bond-breaking process. A steam-to-carbon (S/C) ratio of (3.5) was advantageous for methanol steam reforming (MSR), and a high ethanol concentration of 10–15 vol% was favorable for ethanol steam reforming (ESR). Ni (10 wt%), and Co (10 wt%) were the optimum metal combinations in the catalyst for ethanol reformation at a reforming temperature of 450 °C. The optimum metal catalysts for producing hydrogen and converting ethanol were those synthesized through co-precipitation. The peak hydrogen yield was attained at the sintering temperature of 560–570 °C. ANN technique is cost-effective, quick, and precise, with vast potential to produce hydrogen energy, and may give significant benefits for industrial applications.