Investigation of syngas exergy value and hydrogen concentration in syngas from biomass gasification in a bubbling fluidized bed gasifier by using machine learning

Abstract

In this study, an artificial neural network (ANN) model as a machine learning method has been employed to investigate the exergy value of syngas, where the hydrogen content in syngas reached maximum in bubbling fluidized bed gasifier which is developed in Aspen Plus® and validated from experimental data in literature. Levenberg-Marquardt algorithm has been used to train ANN model, where oxygen, hydrogen and carbon contents of sixteen different biomass, gasification temperature, steam and fuel flow rates were selected as input parameters of the model. Moreover, four different biomass samples, which hadn't been used in training and testing, have been used to create second validation. The hydrogen mole fraction of syngas was also evaluated at the different steam to fuel ratio and gasification temperature and the exergy value of syngas at the point where the hydrogen content in syngas reached maximum were estimated with low relative error value.