Study on Storage Characteristic of Navel Orange Based on ANN

In order to predict storage life of navel orange, The model for the variable regularity of total soluble sugar, total acidity, vitamin C, soluble solids, the sugar-acidity ratio in navel orange according to storage time was established based on BP artificial neural network . The results show that the multi-factor BP artificial neural network model has better predicted effect than single-factor one. When the number of the hidden layer neuron is 8, the multi-factor BP artificial neural network model of total soluble sugar, total acidity, vitamin C, soluble solids, the sugar-acidity ratio according to storage time was the most accurate, the correlation coefficient R between prediction and true value of storage time reached 0.98, the prediction and true value of the model was 0.99. As a result, the multi -factor BP artificial neural network model could be used to predict the navel orange storage life.