Abstract
This researched is about to evaluate and make a comparison between the prediction and simulating efficiencies of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) based on models on sugar fermentable by using empty fruit bunch fiber (EFBF) as a feedstock for bioethanol production. In statistics, response surface methodology (RSM) explores the relationships between several explanatory variables and one or more response variables. The parameters were obtain which are enzyme concentration, substrate concentration and time for using and applying in the RSM. The Artificial Neural Network (ANN) model was developed using MATHLAB Neural Network Toolbox to optimize the enzymatic hydrolysis from the 19 sets of experimental data. Based on the result obtained from both models, it indicates that both RSM and ANN models were fitted well to experimental data. However, ANN model showed a slight edge over RSM model due to higher value of R2 The R2 calculated from validation data for RSM and ANN models were 0.9812 and 0.999833 respectively. Thus, it is proven that ANN model is more powerful tool for modeling and optimization of the empty fruit bunch fiber for sugar fermentation production in term of the reducing sugar yield.
Metadata
Item Type: | Student Project |
---|---|
Creators: | Creators Email / ID Num. Dewa Safri, Amirul Iqbal 2012275366 |
Contributors: | Contribution Name Email / ID Num. Thesis advisor Sanusi, Salmi Nur Ain 317612 |
Subjects: | Q Science > QK Botany > Plant physiology > Physical plant physiology > Growth. Development. Including pattern formation T Technology > TP Chemical technology > Fuel > Biomass |
Divisions: | Universiti Teknologi MARA, Johor > Pasir Gudang Campus > Faculty of Chemical Engineering |
Programme: | Diploma Chemical Engineering |
Keywords: | Artificial Neural Network (ANN), Bioethanol production, UiTM Pasir Gudang |
Date: | 2015 |
URI: | https://ir.uitm.edu.my/id/eprint/40820 |
Download
40820.pdf
Download (212kB)