A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Optimization of biohydrogen production by Enterobacter species using artificial neural network and response surface methodology
Optimization studies on fermentative hydrogen production were investigated using a facultative bacteria namely, Enterobacter species (MTCC 7104). The present study emphasizes the application of mathematical tools such as response surface methodology (RSM) and artificial neural network (ANN) to predict the maximum yield of hydrogen from the optimized carbon and nitrogen source. The key components such as glucose, initial pH, xylose, tryptone, yeast extract, sucrose, and peptone were screened using the Plackett-Burman design. Furthermore, rotatable central composite design and analysis of variance were adopted to investigate the interactive effect of the significant variables (xylose concentration, initial pH, and peptone concentration). Maximum experimental hydrogen yield of 1.94 mol H2/mol xylose was achieved at the optimal points predicted by the RSM. Modeling ability of ANN and RSM has also been evaluated on predicting the maximum hydrogen yield with the estimated values of root mean square error (RMSE), multiple correlation coefficients (R2), and standard error of prediction (SEP). The estimated values of RMSE, R2, and SEP for ANN model and RSM model confirm that fitness and prediction accuracy of ANN model were higher when compared to RSM model. Energy conversion efficiency and energy recovery analysis were performed for hydrogen production process using xylose as the source material.
Optimization of biohydrogen production by Enterobacter species using artificial neural network and response surface methodology
Optimization studies on fermentative hydrogen production were investigated using a facultative bacteria namely, Enterobacter species (MTCC 7104). The present study emphasizes the application of mathematical tools such as response surface methodology (RSM) and artificial neural network (ANN) to predict the maximum yield of hydrogen from the optimized carbon and nitrogen source. The key components such as glucose, initial pH, xylose, tryptone, yeast extract, sucrose, and peptone were screened using the Plackett-Burman design. Furthermore, rotatable central composite design and analysis of variance were adopted to investigate the interactive effect of the significant variables (xylose concentration, initial pH, and peptone concentration). Maximum experimental hydrogen yield of 1.94 mol H2/mol xylose was achieved at the optimal points predicted by the RSM. Modeling ability of ANN and RSM has also been evaluated on predicting the maximum hydrogen yield with the estimated values of root mean square error (RMSE), multiple correlation coefficients (R2), and standard error of prediction (SEP). The estimated values of RMSE, R2, and SEP for ANN model and RSM model confirm that fitness and prediction accuracy of ANN model were higher when compared to RSM model. Energy conversion efficiency and energy recovery analysis were performed for hydrogen production process using xylose as the source material.
Optimization of biohydrogen production by Enterobacter species using artificial neural network and response surface methodology
Karthic, P. (author) / Joseph, Shiny (author) / Arun, Naveenji (author) / Kumaravel, S. (author)
Journal of Renewable and Sustainable Energy ; 5 ; 033104-
2013-05-01
12 pages
Article (Journal)
Electronic Resource
English
Optimizing Wood Composite Drilling with Artificial Neural Network and Response Surface Methodology
| DOAJ | 2024
Biohydrogen production using anaerobic mixed bacteria: Process parameters optimization studies
| American Institute of Physics | 2013