Enzymatic hydrolysis of sugarcane bagasse for bioethanol production: determining optimal enzyme loading using neural networks

BACKGROUND: The efficient production of a fermentable hydrolyzate is an immensely important requirement in the utilization of lignocellulosic biomass as a feedstock in bioethanol production processes. The identification of the optimal enzyme loading is of particular importance to maximize the amount of glucose produced from lignocellulosic materials while maintaining low costs. This requirement can only be achieved by incorporating reliable methodologies to properly address the optimization problem. RESULTS: In this work, a data-driven technique based on artificial neural networks and design of experiments have been integrated in order to identify the optimal enzyme combination. The enzymatic hydrolysis of sugarcane bagasse was used as a case study. This technique was used to build up a model of the combined effects of cellulase (FPU/L) and beta-glucosidase (CBU/L) loads on glucose yield (%) after enzymatic hydrolysis. The optimal glucose yield, above 99%, was achieved with cellulase and beta-glucosidase concentrations in the ranges of 460.0 to 580.0 FPU L-1 (15.3-19.3 FPU g(-1) bagasse) and 750.0 to 1140.0 CBU L-1 (2-38 CBU g(-1) bagasse), respectively. CONCLUSIONS: The dynamic model developed can be used not only to the prediction of glucose concentration profiles for different enzymatic loadings, but also to obtain the optimum enzymes loading that leads to high glucose yield. It can promote both a successful hydrolysis process control and a more effective employment of enzymes. (C) 2010 Society of Chemical Industry