Study on Thermal Conductivities Prediction for Apple Fruit Juice by Using Neural Network
In: IFIP Advances in Information and Communication Technology ; 4th Conference on Computer and Computing Technologies in Agriculture (CCTA) ; https://hal.inria.fr/hal-01562726 ; 4th Conference on Computer and Computing Technologies in Agriculture (CCTA), Oct 2010, Nanchang, China. pp.198-204, ⟨10.1007/978-3-642-18336-2_23⟩, 2010
Online
Konferenz
Zugriff:
International audience ; 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 absolute 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.
Titel: |
Study on Thermal Conductivities Prediction for Apple Fruit Juice by Using Neural Network
|
---|---|
Autor/in / Beteiligte Person: | Zhang, Min ; Che, Zhenhua ; Lu, Jiahua ; Zhao, Huizhong ; Chen, Jianhua ; Zhong, Zhiyou ; Yang, Le ; Shanghai Ocean University ; University of Shanghai for Science and Technology ; Li, Daoliang ; Liu, Yande ; Chen, Yingyi ; 12, TC |
Link: | |
Zeitschrift: | IFIP Advances in Information and Communication Technology ; 4th Conference on Computer and Computing Technologies in Agriculture (CCTA) ; https://hal.inria.fr/hal-01562726 ; 4th Conference on Computer and Computing Technologies in Agriculture (CCTA), Oct 2010, Nanchang, China. pp.198-204, ⟨10.1007/978-3-642-18336-2_23⟩, 2010 |
Veröffentlichung: | HAL CCSD ; Springer, 2010 |
Medientyp: | Konferenz |
DOI: | 10.1007/978-3-642-18336-2_23 |
Schlagwort: |
|
Sonstiges: |
|