Gas–solid
fluidized beds are complex particle systems, and
the electrostatic behavior of particles in fluidized beds is even
more complex, which is influenced by numerous factors such as particle
properties and operating conditions. Current studies focus on the
effect of a certain factor on particle charging without a global picture.
Furthermore, there is no mathematical model that can describe the
interaction of multiple factors on particle charging because it is
difficult to build a model for such a complex system. Therefore, a
new approach is needed. In this study, a model capable of accurately
predicting the surface charge density of particles in monodispersed
gas–solid fluidized beds within a certain range was developed
based on the literature and experimental data through several machine
learning methods including kernel ridge regression (KRR), support
vector machine regression (SVR), and multilayer perceptron (MLP).
SVR and MLP models gave the best results with
R
2
equal to 0.980 and 0.979, respectively. However, the sensitivity
analysis showed that the MLP model was more reliable than the SVR
model. In conclusion, the feasibility of using machine learning to
analyze the charging behavior of particles in fluidized beds is demonstrated,
and the proposed MLP model can serve as an accurate correlative tool
for fast and effective estimation of particle surface charge density
in gas–solid fluidized beds.