Modeling of Hydrogen Production by Applying Biomass Gasification: Artificial Neural Network Modeling Approach

In order to accurately anticipate the proficiency of downdraft biomass gasification linked with a water–gas shift unit produce biohydrogen, model based on an artificial neural network (ANN) approach is established estimate specific mass flow rate biohydrogen output plant different types biomasses and diverse operating parameters. The factors considered as inputs models are elemental proximate analysis compositions well structure includes one layer for input, hidden layer. One thousand eight hundred samples derived from simulation 50 various feedstocks in situations were utilized train developed ANN model. case product presents satisfactory agreement input data: absolute fraction variance (R2) more than 0.999 root mean square error (RMSE) lower 0.25. addition, relative impact properties parameters studied. At end, have comprehensive evaluation, variations regarding hydrogen-content compared evaluated together. results show that almost all significant smhydrogen output. Significantly, gasifier temperature, SBR, moisture content hydrogen highest impacts contributions 19.96, 17.18, 15.3 10.48%, respectively. other variables feed properties, like C, O, S N present range 1.28–8.6% components VM, FC A 3.14–7.67% smhydrogen.