ef0c00822_si_001.pdf (2.74 MB)
Novel Sensitivity Study for Biomass Directional Devolatilization by Random Forest Models
journal contribution
posted on 2020-06-30, 19:36 authored by Jiangkuan Xing, Kun Luo, Haiou Wang, Tai Jin, Jianren FanDevolatilization
is always the primary process in biomass thermal
conversion, and directional devolatilization has caught considerable
attention in recent decades for producing certain fuels and raw chemical
materials. In the present study, we report a novel sensitivity study
for biomass directional devolatilization using random forest models,
which shows obvious advantages in the parameter range, analysis time,
and cost compared with the experimental approach. First, a biomass
devolatilization product database is constructed with a detailed mechanism
for various biomass types under different operation conditions. Then
random forest models are developed from the constructed database to
accelerate the Sobol sensitivity analysis for obtaining the full-parameter-effect
phase diagram. The phase diagram shows that the cellulose fraction
holds the maximum influence for the CH4, C2H4, CO, and tar yields, while it has has limited effects on
the H2O, CO2, and solid residue (SR) yields.
The final temperature has the maximum effect on the H2 yield,
and the LIG-C fraction shows the dominating effect on the SR yield.
The final temperature and the LIG-C fraction have comparable and considerable
effects on the H2O yield. This full-parameter phase diagram
provides an efficient way to directionally choose the biomass types
and alter the operation conditions to produce certain devolatilization
products.
History
Usage metrics
Keywords
biomass devolatilization product da...full-parameter phase diagramforest modelsoperation conditionsfull-parameter-effect phase diagramCHCOSobol sensitivity analysisLIG-C fractionH 2 Obiomass typesyieldC 2 H 4Biomass Directional DevolatilizationNovel Sensitivity StudyRandom Forest Models DevolatilizationSRnovel sensitivity study
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC