Hybrid neural network modeling and particle swarm optimization for improved ethanol production from cashew apple juice

A hybrid neural model (HNM) and particle swarm optimization (PSO) was used to optimize ethanol production by a flocculating yeast, grown on cashew apple juice. HNM was obtained by combining artificial neural network (ANN), which predicted reaction specific rates, to mass balance equations for substrate (S), product and biomass (X) concentration, being an alternative method for predicting the behavior of complex systems. ANNs training was conducted using an experimental set of data of X and S, temperature and stirring speed. The HNM was statistically validated against a new dataset, being capable of representing the system behavior. The model was optimized based on a multiobjective function relating efficiency and productivity by applying the PSO. Optimal estimated conditions were: S-0 = 127 g L-1, X-0 = 5.8 g L-1, 35 degrees C and 111 rpm. In this condition, an efficiency of 91.5% with a productivity of 8.0 g L-1 h(-1)was obtained at approximately 7 h of fermentation.

Automated summary

The study utilized a hybrid neural model and particle swarm optimization to optimize ethanol production by a flocculating yeast grown on cashew apple juice. The model, combining artificial neural network and mass balance equations, was validated statistically and optimized using a multiobjective function. Optimal conditions resulted in high efficiency and productivity during fermentation.