Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology (RSM), artificial neural networks (ANN), and fuzzy inference system (FIS): A comparative evaluation
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Abstract
Levulinic acid is recognized as a prominent value-added chemical that can be obtained from bioresources and has versatile industrial applications. This work reports bioprocess modeling of levulinic acid synthesis from sugarcane bagasse employing response surface methodology and artificial intelligence techniques, including artificial neural network and fuzzy inference system approaches. The influence of process parameters, namely reaction temperature, concentration of levulinic acid and reaction time on the production of levulinic acid was investigated. The levulinic acid production values predicted by empirical models were compared with experimentally acquired data. The predictive capability of various models was appraised by computing statistical indices. The artificial neural network model was determined to be the best predictive model with the highest coefficient of determination value of 0.96 and the lowest error values (root mean square error = 0.272, mean absolute error = 0.072 and mean absolute percentage deviation = 2 %). The feedforward back propagation network with 3–10-1 architecture was employed to model the production of levulinic acid. The process optimization was performed using the desirability function approach. The bagasse, on treatment under optimum conditions, with 1 M sulphuric acid at 190 °C for 15 min yielded 5.40 mg/mL levulinic acid accounting for 77.1 % process efficiency. The utilization of waste biomass sugarcane bagasse would offer a sustainable approach for the production of platform chemical levulinic acid.
Description
Abstract. Full text available at https://doi.org/10.1016/j.fuel.2022.125409
Keywords
Levulinic acid, Sugarcane bagasse, Response surface methodology, Artificial neural networks, Fuzzy inference system, Bagasse, Modeling, Modeling techniques, Predictive modeling
Citation
Ogedjo, M., Kapoor, A., Kumar, P. S., Rangasamy, G., Ponnuchamy, M., Rajagopal, M., & Banerjee, P. N. (2022). Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology (RSM), artificial neural networks (ANN), and fuzzy inference system (FIS): A comparative evaluation. Fuel, 329, 125409.