Hydrogen Production by Fluidized Bed Reactors: A Quantitative Perspective Using the Supervised Machine Learning Approach

Abstract

The current hydrogen generation technologies, especially biomass gasification using fluidized bed reactors (FBRs), were rigorously reviewed. There are involute operational parameters in a fluidized bed gasifier that determine the anticipated outcomes for hydrogen production purposes. However, limited reviews are present that link these parametric conditions with the corresponding performances based on experimental data collection. Using the constructed artificial neural networks (ANNs) as the supervised machine learning algorithm for data training, the operational parameters from 52 literature reports were utilized to perform both the qualitative and quantitative assessments of the performance, such as the hydrogen yield (HY), hydrogen content (HC) and carbon conversion efficiency (CCE). Seven types of operational parameters, including the steam-to-biomass ratio (SBR), equivalent ratio (ER), temperature, particle size of the feedstock, residence time, lower heating value (LHV) and carbon content (CC), were closely investigated. Six binary parameters have been identified to be statistically significant to the performance parameters (hydrogen yield (HY)), hydrogen content (HC) and carbon conversion efficiency (CCE)) by analysis of variance (ANOVA). The optimal operational conditions derived from the machine leaning were recommended according to the needs of the outcomes. This review may provide helpful insights for researchers to comprehensively consider the operational conditions in order to achieve high hydrogen production using fluidized bed reactors during biomass gasification.

A review on thermochemical based biorefinery catalyst development progress

“…57 The main sub-divisions of the fluidized-bed reactor are a bubbling fluidized-bed, circulating fluidized-bed, dual-bed indirect and entrained-bed ones. 53,58 The main difference between different types of fluidized-bed reactors is the speed of the gasification agent or the type of its contact with the biomass. For instance, in the bubbling fluidized-bed design, the speed of fluidization is in the range of 1–3 m s −1 .…”

Fluidized Bed Scale-Up for Sustainability Challenges. 1. Tomorrow’s Tools

“…Kim et al used RF and ANN to optimize syngas production from a fluidized bed biomass gasifier. A similar approach was employed by Lian et al for the production of hydrogen from a fluidized bed reactor. Indeed, ML methods for process monitoring, fault detection, and soft sensing are already commercially implemented .…”

Fluidized Bed Scale-Up for Sustainability Challenges. 2. New Pathway

“…Fu et al 73 used an artificial neural network model (ANN) to optimize the pressure drop and expansion ratio for fluidized bed reactors. Kim et al 74 used RF and ANN to maximize syngas produced by a fluidized bed biomass gasifier, while Lian et al 75 employed similar methods to maximize hydrogen. Machine learning tools thus are useful to augment the scale-up process with new insights not obtainable by more traditional methods.…”