شماره ركورد كنفرانس :
5048
عنوان مقاله :
Modeling of apple drying using artificial neural network (MLP)
Author/Authors :
M ،Nikzad Faculty of Chemical Engineering - Mazandaran University - Babol, Iran , K ،Movagharnejad Faculty of Chemical Engineering - Mazandaran University - Babol, Iran , F ،Asghari Katisari Faculty of Chemical Engineering - Mazandaran University - Babol, Iran , S ،Fatemi Faculty of Chemical Engineering - Mazandaran University - Babol, Iran
كليدواژه :
artificial neural network , moisture ratio , drying , apple
عنوان كنفرانس :
ششمين كنگره بين المللي مهندسي شيمي
چكيده لاتين :
In this study drying of apple was studied at different thickness and type of tray. Page model was tested to fit the
moisture ratio of apple. Artificial neural network (ANN) is a technique with flexible mathematical structure which is
capable of identifying complex non-linear relationship between input and output data. A multi layer perceptron (MLP)
neural network was used to predict the moisture ratio of apple during drying. A 3-18-1 structure provided the least
errors. In addition a three-layer feed-forward neural network was used to estimate the moisture ratio of apple. A back
propagation algorithm was developed (using MATLAB ) and applied to training and testing the network. It was found
that the estimated moisture ratio by multi layer perceptron neural network is more accurate than Page’s model. The
results were compared with experimental data. It was also found that moisture ratio decreased with increasing of drying
time.
