Prediction of tar and particulate in biomass gasification using adaptive neuro fuzzy inference system

Biomass is an important primary source of renewable energy source. Producer gas, a derivative of Biomass, comprises of tar and particulate content which is harmful and critical parameter for IC engine application, which influences the design of filter. Numerous researchers have developed various typ...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent & fuzzy systems 2014, Vol.27 (1), p.361-365
Main Authors: Rameshkumar, R., Mayilsamy, K.
Format: Article
Language:English
Subjects:
Adaptive systems
Artificial neural networks
Biomass
Design engineering
Fuzzy logic
Gasification
Mathematical models
Producer gas
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Biomass is an important primary source of renewable energy source. Producer gas, a derivative of Biomass, comprises of tar and particulate content which is harmful and critical parameter for IC engine application, which influences the design of filter. Numerous researchers have developed various types of filter for gas cleaning system in order to reduce the tar content and particulate in producer gas. In this work, an experimental investigation has been carried out on the newly developed hybrid compact filter using two different feeds such as rice husk and wood. The experimental results obtained were used to justify the newly developed system with adaptive neuro-fuzzy inference system(ANFIS). The data has been collected taken from an experimental database of a 20 kW open core downdraft TNAU(Tamil Nadu Agricultural University)-modified gasifier with compact hybrid filter system. A comparison between the predictions of ANFIS model with other available model in literature is presented. The ANFIS results reveal that the model delivers the tar and particulate content with an accuracy of 99.98%. The test results prove the possibility to develop and evaluate an ANFIS based model to predict tar content and particulate for any filter design under varying input conditions.
ISSN:1064-1246
DOI:10.3233/IFS-131004