Prediction of Temperature, Moisture And Fat Contents In Meatballs During Deep-Fat Frying Using Artificial Neural Network

摘要

An Artificial Neural Network (ANN) was developed to predict heat and mass transfer during deep-fat frying of meatballs. Frying time, meatbal radius, fat diffusivity, moisture diffusivity, heat transfer coefficient, fat conductivity, initial moisture content, thermal diffusivity, initial meatball temperature, and oil temperature were input variables. Temperature at meatball geometric centre (T_o), average temperature of meatball (T_(ave)), average fat content of meatball (mf_(ave)), and average moisture content of meatball (m_(ave)) were outputs. The data used to train and verify the ANN were obtained from validated simulation models. ANN with 60 hidden notes in a layer with learning rate = 0.5 and momentum = 0.3 provided the lowest errors. The mean relative errors for T_o, T_(ave), m_(ave) and mf_(ave) were 0.542%, 0.145%, 0.032% and 0.100% respectively. Heat transfer coefficient had the minimum influnce on all the outputs. Trained ANN can be used to predict outputs during deep-fat frying of meatballs with high precision.