Air gasification of high-ash sewage sludge for hydrogen production: Experimental, sensitivity and predictive analysis

Abstract

In this work, air gasification of sewage sludge was conducted in a lab-scale bubbling fluidized bed gasifier. Further, the gasification process was modeled using artificial neural networks for the product gas composition with varying temperatures and equivalence ratios. Neural network-based prediction will help to predict the hydrogen production from product gas composition at various temperatures and equivalence ratios. The gasification efficiency and lower heating values were also established as a function of temperatures and equivalence ratios. The maximum H2 and CO was recorded as 16.26 vol% and 33.55 vol%. Intraileally at ER 0.2 gas composition H2, CO, and CH4 show high concentrations of 20.56 vol%, 45.91 vol%, and 13.32 vol%, respectively. At the same time, CO2 was lower as 20.20 vol% at ER 0.2. Therefore, optimum values are suggested for maximum H2 and CO yield and lower concentration of CO2 at ER 0.25 and temperature of 850 °C. A predictive model based on an Artificial Neural network is also developed to predict the hydrogen production from product gas composition at various temperatures and equivalence ratios. The network has been trained with different topologies to find the optimal structure for temperature and equivalence ratio. The obtained results showed that the regression coefficients for training, validation, and testing are 0.99999, 0.99998, and 0.99992, respectively, which clearly identifies the training efficiency of the trained model.