Comparative Assessment of the Artificial Neural Network and Response Surface Modelling Efficiencies for Biohydrogen Production on Sugar Cane Molasses
- 428 Downloads
This study comparatively evaluates the modelling efficiency of the Response Surface Methodology (RSM) and the Artificial Neural Network (ANN). Twenty-nine biohydrogen fermentation batches were carried out to generate the experimental data. The input parameters consisted of a concentration of molasses (50–150 g/l), pH (4–8), temperature (35–40 °C) and inoculum concentration (10–50 %). The obtained data were used to develop the RSM and ANN models. The ANN model was a committee of networks with a topology of 4-(6-10)-1 structured on multilayer perceptrons. RSM and ANN models gave R2 values of 0.75 and 0.91, respectively, with predicted optimum conditions of 150 g/l, 8 and 35 °C for molasses, pH and temperature, respectively, with differences in inoculum concentrations (10.11 and 15 %) for RSM and ANN, respectively. Upon validation, 15.12 and 119.08 % prediction errors on hydrogen volume were found for ANN and RSM, respectively. These findings suggest that ANN has greater accuracy in modelling the relationships between the considered process inputs for fermentative biohydrogen production and thus, is more reliable to navigate the optimization space.
KeywordsBiohydrogen production Dark fermentation Artificial neural network Response surface model Genetic algorithm
The financial assistance of the National Research Foundation (NRF) towards this research is hereby acknowledged. Opinions expressed and conclusions arrived at, are those of the authors and are not necessarily to be attributed to the NRF.
- 3.Pandu K, Joseph S (2012) Comparisons and limitations of biohydrogen production processes: a review. Int J Adv Eng Technol 2(1):342–356Google Scholar
- 9.Gueguim Kana EB, Oloke JK, Lateef A, Adesiyan MO (2012) Modelling and optimization of biogas production on saw dust and other co-substrates using artificial neural network and genetic algorithm. Renew Energy 46:276–281Google Scholar
- 11.Gueguim Kana EB, Oloke JK, Lateef A, Oyebanji A (2012) Comparative evaluation of artificial neural network coupled genetic algorithm and response surface methodology for modelling and optimization of citric acid production by Aspergillus niger MCBN297. Chem Eng Trans 27:397–402Google Scholar
- 17.Frankfort-Nachmias C, Leon-Guerrero A (2011) Social statistics for a diverse society, 6th edn. Pine Forge, USA, pp 1–537Google Scholar
- 19.Lin CY, Lin CY, Wu JH, Chen CC (2007) Effect of a thermal pretreatment of influent on the fermentative hydrogen production from molasses. J Environ Eng Manage 17(2):117–122Google Scholar
- 20.Kotay SM, Das D (2006) Microbial hydrogen production with Bacillus coagulans IIT-BT S1 isolated from anaerobic sewage sludge. Bioresour Technol 1–8Google Scholar
- 21.Khanal SK, Chen WH, Li L, Sung S (2004) Biological hydrogen production: effects of pH and intermediate products. Int J Hydrog Energy 29:1123–1131Google Scholar
- 25.YossanS O-TS, Prasertsan P (2012) Effect of initial pH, nutrients and temperature on hydrogen production from palm oil mill effluent using thermotolerant consortia and corresponding microbial communities. Int J Hydrog Energy 37:13807–13814Google Scholar
- 26.Adams MWW, Mortenson LE (1984) The physical and catalytic properties of hydrogenase II of Clostridium pasteurianum: a comparison with hydrogenase I. 259 (11):7045–7055Google Scholar
- 28.Veena T, Tiwari KL, Quraishi A, Jadhav SK (2012) Biohydrogen production from rice mill effluent. J Appl Sci Environ Sanit 7(4):237–240Google Scholar