Optimization of Hydrogen Production from Sewage Sludge using Machine Learning Methods Integrated with Genetic Algorithm

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