期刊
FUEL
卷 289, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.fuel.2020.119903
关键词
Municipal solid waste; Gasification; Porous media; Soft computing approaches; Optimised ensemble model
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.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据