Abstract
Understanding the hydrodynamic behavior of irregular-shaped particles is vital for optimizing fluidized bed systems. In this study, the effect of binary and ternary biomass mixtures of silica sand in a gas–solid fluidized bed on pressure drop (Δ P / H ) profiles was investigated experimentally as a function of superficial gas velocity ( U g ). It was observed that using a mixture of particles increases the overall complexity of the system. The experimental results were also used to develop an artificial neural network (ANN) model. The five dimensionless parameters were used to train the network with the expected output of the Δ P / H profiles. The statistical analyses were used to compare the performance of the model between one and two hidden layers. The results showed that the ANN model with only one hidden layer could accurately predict the fluidization behavior with an R 2 of 0.95.
Publication details
- Authors: Soanuch, C., Pareek, V., Piumsomboon, P., Chalermsinsuwan, B.
- Published in: (2023) Industrial & Engineering Chemistry Research, 62 (43), pp. 18079-18090.
- Year: 2023
- DOI: 10.1021/acs.iecr.3c03105