Robust modelling development for optimisation of hydrogen production from biomass gasification process using bootstrap aggregated neural network

In this study, a robust model using bootstrapped aggregated neural network (BANN) was developed for optimising operating conditions of a two-stage gasification for high carbon conversion, high hydrogen yield and low CO₂. The developed BAAN model predicted accurately (R² of 0.999) the gas composition and the 95% confidence bounds for model predictions on unseen validation data indicated good prediction reliability for various feedstock. The BANN was also used to predict the optimum operating condition for hydrogen production from waste wood (1st stage temperature of 900 °C, 2nd stage temperature of 1000 °C, steam/carbon molar ratio of 5.7) to achieve high hydrogen (71–72 mol%), gas yield (98–99 wt%) and low CO₂ (17–18 mol%). The optimal conditions were tested in the laboratory and the experimental results agreed well with the predicted data with an error of 0.01–0.05. Sensitivity analysis revealed that an increase in temperatures for both stages and high steam/carbon ratio favoured the H₂ production and carbon conversion.     

Optimisation of Manufacturing Parameters for an Ni–Ag Fuel Cell Electrode

The aim of this research is to optimise manufacturing parameters for a fuel cell electrode. The combination of nickel oxide, silver oxide and ammonium bicarbonate powders is used to produce the electrode. The main role of silver element is to increase the activity in the electrode. Ni–Ag electrode can be used in fuel cells as positive and negative electrodes. All powders are mixed in the benzene solution by a magnetic mixer and then compressed to form green electrode. The range of pressure in this step is between 40 and 160 MPa. The green electrode is sintered in hydrogen atmosphere through a tube furnace and then cooled to 200 °C under argon atmosphere. The range of sintering temperature and time is 500–800 °C and 10–60 min, respectively. Also, silver oxide and ammonium bicarbonate percentages are varied from 20 to 65 and 15 to 35%, respectively. All parameters including composition, pressure, sintering temperature and time are changed during electrode fabrication to achieve optimised properties in the electrode. So, it is necessary to perform several tests measuring porosity, surface area, density, weight loss, mechanical strength, shrinkage, exchange current density and metallographic photos. The optimum conditions of the electrode production resulting from this investigation include compacting pressure 60 MPa, sintering temperature 560 °C, sintering time 15 min, silver oxide percentage 50% and ammonium bicarbonate percentage 27%.