 Fuzzy logic-based predictive model for biomass pyrolysisNuttapol Lerkkasemsan Applied Energy, 2017, vol. 185, issue P2, 1019-1030 Abstract: As pyrolysis reaction is one of an important reaction applied to lignocellulosic biomass in order to transform it to be user-friendly energy form recognized as prospective alternative energy source, the reaction has been widely investigated in order to understand the mechanisms and kinetics of the pyrolysis. However, modeling pyrolysis of biomass is full of complication. As lignocellulosic biomass is not a homogeneous chemical source, chemical compositions in biomass are also uncertain and they vary even in the same biomass. The reactions of imprecise chemical compositions in biomass affects the capability of deterministic model in modeling chemical reaction since available deterministic models are designed to model homogeneous and precise chemical compositions. With this problem, it raises the idea of using model which has ability to calculate something ambiguous. Since the fuzzy logic-based model which is adaptive network-based fuzzy inference system (ANFIS) is built to calculate uncertainty, the model should be suitable to handle uncertainty which is imprecise chemical compositions in the reaction. The proposed model is built with four input variables: the reaction time, amount of cellulose component, amount of hemicellulose component, and amount of lignin component in biomass. The model is trained with tuning datasets which are the pyrolysis datasets of lignin, cellulose and Madhuca before applying to predict the pyrolysis reactions of Pongamia pinnata and Jatropha curcas. The comparative results show that the proposed model can correctly predict 91.82% and 97.29%, respectively, of the pyrolysis reactions of P. pinnata and J. curcas. As the ANFIS model gives good prediction in modeling pyrolysis of two different biomasses, the model can be applied to predict the pyrolysis reaction of other lignocellulosic biomass products. Keywords: Pyrolysis of biomass; Predictive modeling; Fuzzy logic (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:185:y:2017:i:p2:p:1019-1030 Ordering information: This journal article can be ordered from DOI: 10.1016/j.apenergy.2016.02.105 Access Statistics for this article Applied Energy is currently edited by J. Yan More articles in Applied Energy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.