Please use this identifier to cite or link to this item:
|Title:||Thermosiphon solar domestic water heating systems: long-term performance prediction using artificial neural networks||Authors:||Panteliou, Sofia
Kalogirou, Soteris A.
|Keywords:||Artificial Neural Networks (ANN)||Issue Date:||2000||Publisher:||Elsevier B. V.||Source:||Solar Energy, Vol. 69, no. 2, 2000, pp. 163-174||Abstract:||The objective of this work is to use artificial neural networks (ANN) for the long-term performance prediction of thermosiphonic type solar domestic water heating (SDWH) systems. Thirty SDWH systems have been tested and modelled according to the procedures outlined in the standard ISO 9459-2 at three locations in Greece. From these, data from 27 of the systems were used for training and testing the network while data from the remaining three were used for validation. Two ANNs have been trained using the monthly data produced by the modeling program supplied with the standard ISO 9459-2. Different networks were used depending on the nature of the required output, which is different in each case. The first network was trained to estimate the solar energy output of the system for a draw-off quantity equal to the storage tank capacity (at the end of the solar energy collection period) and the second one was trained to estimate the solar energy output of the system and the average quantity of hot water per month at demand temperatures of 35 and 40°C. The collector areas of the considered systems were varying between 1.81 m2 and 4.38 m2. Open and closed thermosiphonic systems have been considered both with horizontal and vertical storage tanks. In this way the networks were trained to accept and handle a number of unusual cases. The input data in both networks are similar to the ones used in the program supplied with the standard. These were the size and performance characteristics of each system and various climatic data. In the second network the demand temperature was also used as input. For the first network the statistical coefficient of multiple determination (R2-value) obtained for the training data set was equal to 0.9993. For the second network the R2-value for the two output parameters was equal to 0.9848 and 0.9926, respectively. Unknown data were subsequently used to investigate the accuracy of prediction and R2-values equal to 0.9913 for the first network and 0.9733 and 0.9940 for the second were obtained. These results indicate that the proposed method can successfully be used for the prediction of the solar energy output of the system for a draw-off equal to the volume of the storage tank or for the solar energy output of the system and the average quantity of the hot water per month for the two demand water temperatures considered.||URI:||http://ktisis.cut.ac.cy/handle/10488/193||ISSN:||0038-092X||DOI:||10.1016/S0038-092X(00)00058-X||Rights:||Copyright © 2000 Elsevier Science Ltd. All rights reserved.|
|Appears in Collections:||Άρθρα/Articles|
Show full item record
WEB OF SCIENCETM
checked on Aug 22, 2017
checked on Aug 22, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.