Artificial neural network approach for the steam gasification of palm oil waste using bottom ash and CaO
The Artificial Neural Network (ANN) modelling is presented for the steam gasification of palm kernel shell using CaO adsorbent and coal bottom ash as a catalyst. The effect of the parameters such as; temperature, CaO/biomass ratio and Coal bottom ash wt. at fixed steam/biomass ratio and steam/biomas...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Published: |
2019
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053190948&doi=10.1016%2fj.renene.2018.07.142&partnerID=40&md5=22a27e93c1447ea493f65ab5e5fdcd0b http://eprints.utp.edu.my/22129/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The Artificial Neural Network (ANN) modelling is presented for the steam gasification of palm kernel shell using CaO adsorbent and coal bottom ash as a catalyst. The effect of the parameters such as; temperature, CaO/biomass ratio and Coal bottom ash wt. at fixed steam/biomass ratio and steam/biomass ratio at the fixed temperature on product gas composition of H2, CO, CO2, and CH4 are modelled using ANN. The effect of parameters is used as an input, while the gas compositions, syngas yield, LHVgas and HHVgas of gas as the output of the network. Back propagation algorithm has been used for the training with 7 neurons in the hidden layer. Hence, the selected ANN architecture was (2-7-1). The gas composition predicted by the ANN model are compared with experimental results obtained from pilot scale gasification system that has been reported in our previous study. The ANN predicted results show high agreement with the published experimental values with the coefficient of determination R2 = 0.998 for almost all the cases, i.e., the effect of parameters. RMSE, MAD, and AARE have been reported to be very insignificant for the predicted and experimental values. © 2018 Elsevier Ltd |
|---|