Modelling of municipal solid waste gasification using an optimised ensemble soft computing model

Modelling and simulation of municipal solid waste (MSW) gasification process is a complex and computationally expensive task due to the porous structure of MSW and the nonlinear relations amongst various parameters. In this study, to model the MSW gasification in fluidised bed gasifier, an optimised ensemble model (OEM) is established based on five advanced soft computing models, including decision tree (DT), extreme gradient boosting (XGB), random forest (RF), multilayer perceptron (MLP) and support vector regression (SVR). The particle swarm optimisation (PSO) algorithm is employed to optimise the five models. The proposed optimised ensemble model is then implemented to predict the gasification characteristics including heating value of gas (LHV), heating value of gasification products (LHVp) and the syngas yield in the process of MSW gasification. The simulation results reveal that the proposed ensemble model is a promising alternative in modelling the nonlinear complex thermochemical processes, such as MSW gasification. Furthermore, through the analysis of the importance of influential variables, the temperature is found to be the most important variable in the modelling of MSW gasification.

Automated summary

The study develops an optimised ensemble model for simulating MSW gasification process, predicting gasification characteristics, and identifies temperature as the most important variable in the modelling.