Response surface methodology and artificial neural network optimized synthesis of enzymatic 2-phenylethyl acetate in a solvent-free system

• Lipase-catalyzed synthesis of 2-phenylethyl acetate in a solvent-free system.
• RSM and ANN models were used for analyzing and optimizing of the process.
• Both RSM and ANN models were developed successfully under the central composite rotatable design.
• ANN was more precise compared to the RSM for prediction the yield.

2-Phenylethyl acetate (2-PEAc) is a colorless to pale yellow liquid with a floral or fruit odor which has been applied widely in food, perfumes, cosmetics, shampoos, soaps and household products. To conform to the “natural” interests of consumers, a solvent-free system using immobilized lipase to catalyze the transesterification of 2-phenethyl alcohol and vinyl acetate was investigated. The solvent-free system offering the advantages of maximization of substrate concentration and greater volumetric production are benefited for industrial production. In this study, an experimental design was used to develop response surface methodology (RSM) and artificial neural network (ANN) models. The effect of synthesis parameters on the molar conversion of 2-PEAc was evaluated. Two models were statistically compared by the coefficient of determination, root mean square error and absolute average deviation, based on the validation data set. The coefficient of determination (R2) calculated from the validation data for RSM and ANN models were 0.92 and 0.99, respectively. While both models showed good predictions in this study, the ANN model was more precise compared to the RSM model.