TY  - JOUR
TI  - Modeling of bio-oil production by pyrolysis of woody biomass: artificial neural network approach
AB  - This study is dedicated to developing a reliable artificial neural network (ANN) model to model the pyrolysis liquid product (biooil). Some related parameters with the bio-oil yield such as the pyrolysis temperature, duration, catalyst type, catalyst ratio, particlesize, proximate, and ultimate analysis of the biomass were tested. Due to the different characteristics of different biomass typesand pyrolysis methods, only slow and intermediate pyrolysis data from woody biomass were used in modeling. The correlationcoefficients (R) were 0.992, 0.933, and 0.951 for training, validation, and testing, respectively. In order to evaluate the predictabilityof the ANN model, the predicted results were compared with the experimental results that were not introduced before. Thesimulated data were in good agreement with the experimental results indicating the reliability of the developed model. The relativeimpact results revealed that the most important parameter that affects the bio-oil yield was catalyst type (11.4%).
AU  - ozbay, gunay
AU  - KOKTEN, Erkan Sami
DO  - 10.2339/politeknik.659136
PY  - 2020
JO  - Politeknik Dergisi
VL  - 23
IS  - 4
SN  - 1302-0900
SP  - 1255
EP  - 1264
DB  - TRDizin
UR  - http://search/yayin/detay/423661
ER  -