Abstract:
Hydrogen production from the supercritical water gasification (SCWG) of sewage
sludge (SS) is a sustainable and efficient process. However, the challenging and
intricate task for the experimental technique is to find out the correlation between
proximate, ultimate analysis and gasification conditions with Hydrogen production.
This process is complicated, expensive and requires many experimental techniques.
To accurately predict and analyze the effect of input parameters on SCWG of SS
process economically, an efficient model must be developed. Considering economic
viability and ensuring optimization of hydrogen yield, this study considers four
different machine learning (ML) models (Support Vector Machine, Ensembled Tree,
Gaussian Process Regression (GPR), Artificial Neural Network) to predict, analyze
the optimal model, and evaluate SCWG performance. The results suggests that GPR
is favored for predicting Hydrogen yield (R2 > 0.997, RMSE 0.093), and is highly
recommended for dealing with complex variable-target correlation. The partial
dependence plot shows that temperature, moisture content and pressure are among the
effective parameters of SCWG. Furthermore, optimization techniques such as genetic
algorithms are incorporated to optimize hydrogen production by tuning the ML
hyperparameters. Additionally, a Graphical User Interface was developed by utilizing
the optimized GPR model for ease in computing Hydrogen yield
