Optimization of molecular distillation for recovery of tocopherol from rapeseed oil deodorizer distillate using response surface and artificial neural network models.

摘要

Back-propagation artificial neural network and response surface methodology were used to build a predictive model of the combined effects of independent variables influencing the recovery of tocopherol from rapeseed (canola) oil deodorizer distillate. These variables included evaporating temp., feed flow rate and wiper rolling speed. The optimum operating conditions obtained from the quadratic form of the response surface methodology and artificial neural network models were an evaporating temp. of 473 K, a wiper rolling speed of 150 rpm and a feed flow rate of 90 ml/h at a feed temp. of 353 K and under a vacuum of 0.02 torr. The results demonstrated the high predictive accuracy of artificial neural network compared to response surface methodology. The interior relationships between parameters were clearly expressed by response surface methodology.