Production of high calorific value hydrogen-rich combustible gas by supercritical water gasification of straw assisted by machine learning.

ABSTRACT

This article reveals the basic laws of straw supercritical water gasification (SCWG) and provides basic experimental data for the effective utilization of straw. The paper studied the impact of three operational conditions on the production of high-calorific value hydrogen-rich combustible gases through SCWG of straw within a quartz tube reactor. The findings reveal that elevated reaction temperatures, extended residence times, and reduced feedstock concentrations favor the SCWG of straw. When combustible gas contains carbon dioxide, the maximum low heating value (LHV) of the gas is 21 MJ/Nm3. Upon removing carbon dioxide, the LHV of the gas reached 38 MJ/Nm3. Subsequently, a machine learning (ML) model was developed to forecast gas yield and LHV during the SCWG process. The results demonstrate that the model exhibits robust generalization capabilities. ML can be extensively applied to forecast biomass SCWG processes across various operational conditions.