Determination of efficiency of flat-plate solar collectors using neural network approach Adnan So ¨zen * , Tayfun Menlik, Sinan U ¨ nvar Gazi University, Technical Education Faculty, Mechanical Education Department, Teknikokullar, 06503 Ankara, Turkey Abstract In this study, a new formula based on artificial neural network (ANN) technique was developed to determine the efficiency of flat- plate solar collectors. In practice, the ANN model can be used for modeling the efficiency of solar collectors with complex structures when other models may have difficulties. Logistic sigmoid transfer function was used in the network. Meteorological data of summer session (from July to September) for Ankara were used as training data in order to train the neural network. Surface temperature in collector, date, time, solar radiation, declination angle, azimuth angle and tilt angle are used in the input layer of the network. The effi- ciency of flat-plate solar collector is in the output layer. The results show that the maximum and minimum deviations were found 2.558484 and 0.001969, respectively. The advantages of ANN model compared to the conventional testing methods are speed, simplicity, and the capacity of the ANN to learn from examples. Ó 2007 Elsevier Ltd. All rights reserved. Keywords: Solar collector; Flat-plate; Artificial neural network; Efficiency 1. Introduction Due to an increase in conventional energy prices and environmental effects, such as air pollution, global heating, depletion of the ozone layer, greenhouse effects; the use of solar energy has increased, following the energy crisis in 1970. On the other hand, solar energy is being seriously considered for satisfying a part of the energy demand in Turkey, as in the world. Solar energy potential is very high in Turkey, which is located at the Mediterranean at 36° and 42°N latitudes and has a typical Mediterranean climate. The yearly average solar radiation is 3.6 kW h/m 2 day, and the total yearly radiation period is 2610 h. Solar radi- ation incident on a horizontal surface and sunshine dura- tion are measured by all recording stations in Turkey (Kaygusuz & Sarı, 2003). Solar energy collectors are a special kind of heat exchangers that transform solar radiation energy to inter- nal energy of the transport medium (Kalogirou, 2004a). The major component of any solar system is especially the flat-plate solar collectors. This device absorbs the incoming solar radiation and converts it into heat and also transfers this heat to a fluid flowing through the collector (Kalogirou, 2004a). These conversions depend on the abso- lute performances of many different materials such as glaz- ing materials, collector absorbing plates and used fluids. The basic parameter to consider is the solar collector ther- mal efficiency. This is defined as the ratio of the useful energy delivered to the energy incident on the collector aperture (Kalogirou, 2004a). The definitions of various relations that are required in order to determine the useful energy collected and the interaction of the various con- structional parameters on the performance of a solar col- lector are fairly complex. Therefore, this study proposes ANN model to define solar collector efficiency. Although the concept of ANN analysis had been discov- ered 50 years ago it is only in the recent decades that an 0957-4174/$ - see front matter Ó 2007 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2007.08.080 * Corresponding author. Tel.: +90 (312) 202 86 07; fax: +90 (312) 212 00 59. E-mail address: asozen@gazi.edu.tr (A. So ¨ zen). URL: http://w3.gazi.edu.tr/~asozen (A. So ¨ zen). www.elsevier.com/locate/eswa Available online at www.sciencedirect.com Expert Systems with Applications 35 (2008) 1533–1539 Expert Systems with Applications