Paper Information

Journal:   MODARES MECHANICAL ENGINEERING   MARCH 2017 , Volume 16 , Number 12 #F0074; Page(s) 291 To 299.
 
Paper: 

COMPARISON OF DYNAMIC AND STATIC NEURAL NETWORKS IN PREDICTING PERFORMANCE OF PARABOLIC SOLAR DESALINATION

 
 
Author(s):  BANAKAR AHMAD, MOTEVALI ALI*, MONTAZERI MEHDI, MOUSAVI SEYEDI SEYED REZA
 
* DEPARTMENT OF MECHANICS OF BIOSYSTEM ENGINEERING, SARI AGRICULTURAL SCIENCES AND NATURAL RESOURCES UNIVERSITY, SARI, IRAN
 
Abstract: 

In this research with utilization of various neural networks models, the relationship between the amount of water production and the temperature of the vapor with different weather conditions, time of day and several water debits in desalination system equipped with linear solar parabolic concentrator was investigated. The results showed that static and dynamic networks can model the process of producing fresh water with high accuracy. Static neural network can perform the modelling process with higher speed than dynamic neural network. However, it seems that the amount of error using dynamic networks was reduced in process modeling. Coefficient of determination (R2) for training, validation and testing in static networks was 0.9898, 0.9899 and 0.9889, respectively. While coefficient of determination (R2) for training, validation and testing in dynamic networks was 0.9922, 0.9894 and 0.9901, respectively. Also, the amount of mean square error (MSE) in static network for training, validation and testing was 0.0011, 0.0027 and 0.0024, respectively and for dynamic networks was 0.0018, 0.0007 and 0.0004, respectively. Comparison between dynamic and static networks show that the dynamic networks can predict the production of fresh water and vapor temperature according to changes in atmospheric parameters more accurately than the static networks.

 
Keyword(s): PREDICTION, NEURAL NETWORKS MODELLING, SOLAR DESALINATION
 
References: 
  • ندارد
 
  Persian Abstract Yearly Visit 27
 
Latest on Blog
Enter SID Blog