会议专题

Study on Thermal Conductivities Prediction for Apple Fruit Juice by Using Neural Network

Based on experimentally measured values by thermal probe method, the prediction model of thermal conductivities of apple fruit juice as a function of concentration and temperature was studied by neural network method. The optimal neural network was made of two hidden layers and every hidden layer had six neurons. The prediction result shows that the optimal model could predict thermal conductivity with a mean relative error of 0.11%, a mean abso-lute error of 0.00054W/mK, a mean standard error of 0.00039 W/mK, the linear relationship of 0.9993. The calculated precision was higher for BP neural network model than that for dual regression model. The presented results were proved that this model can be used with satisfactory accuracy for the prediction of thermal conductivity of apple fruit juice.

Thermal conductivity Neural network Apple fruit juice

Min Zhang Zhenhua Che Jiahua Lu Huizhong Zhao Jianhua Chen Zhiyou Zhong Le Yang

College of Food Sciences, Shanghai Ocean University, Shanghai, 201306, P. R. China School of Environment and Architecture, University of Shanghai for Science and Technology,Shanghai,

国际会议

The 4th IFIP International on Computer and Computing Technologies in Agriculture and the 4th Symposium on Development of Rural Information(第四届国际计算机及计算机技术在农业中的应用研讨会暨第四届中国农业信息化发展论坛 CCTA 2010)

南昌

英文

198-204

2010-10-22(万方平台首次上网日期,不代表论文的发表时间)