Exergy analysis of an ejector-absorption heat transformer using artificial neural network approach Adnan So ¨zen a, * , Erol Arcakliog ˘lu b a Gazi University, Technical Education Faculty, Mechanical Education Department, Teknikokullar, 06503 Ankara, Turkey b Kırıkkale University, Engineering Faculty, Mechanical Engineering Department, 71450 Kırıkkale, Turkey Received 6 June 2006; accepted 16 June 2006 Available online 17 August 2006 Abstract This paper proposes artificial neural networks (ANNs) technique as a new approach to determine the exergy losses of an ejector- absorption heat transformer (EAHT). Thermodynamic analysis of the EAHT is too complex due to complex differential equations and complex simulations programs. ANN technique facilitates these complicated situations. This study is considered to be helpful in predicting the exergetic performance of components of an EAHT prior to its setting up in a thermal system where the working temper- atures are known. The best approach was investigated using different algorithms with developed software. The best statistical coefficient of multiple determinations (R 2 -value) for training data equals to 0.999715, 0.995627, 0.999497, and 0.997648 obtained by different algo- rithms with seven neurons for the non-dimensional exergy losses of evaporator, generator, absorber and condenser, respectively. Simi- larly these values for testing data are 0.999774, 0.994039, 0.999613 and 0.99938, respectively. The results show that this approach has the advantages of computational speed, low cost for feasibility, rapid turnaround, which is especially important during iterative design phases, and easy of design by operators with little technical experience. Ó 2006 Elsevier Ltd. All rights reserved. Keywords: Absorption; Heat transformer; Simulation; Solar pond; Ejector; Artificial neural network 1. Introduction The ejector-absorption heat transformers (EAHT) are considered as ‘‘future technology’’, which will be important for energy utilisation in 21st century according to the inter- national energy agency (IEA) [1]. These systems can be used to increase solar pond’s temperature and to recover low-level waste heat. Solar ponds are a type of solar collec- tor, which provide an inexpensive means for collecting and storing solar energy at temperatures below 100 °C [2]. At present, there are about fifteen heat transformers operating in industrial plants world-wide [3–6]. Though the water/ lithium bromide mixture has been commercially used as the only mixture in the EAHTs, it has some major disad- vantages such as the low working pressure, its limited gross temperature lift. For these reasons, new working pairs have been proposed in EAHTs [7–11]. The aqua–ammonia com- bination, one of them proposed, was chosen for this study because of their extensive use in absorption systems espe- cially operated by waste heat energy and renewable energy. Energy and exergy methods are well-established meth- ods, used to investigate thermal processes. Considering the first law analysis of thermodynamics, the amount of energy consumed is calculated disregarding the difference between work and heat. The analysis and design of engi- neering systems based on only the first law is not adequate [12]. This is caused by factors such as the application of materials balances, energy balances and equilibrium rela- tionships, which do not adequately show how a system effectively utilises for given energy resources [12]. In the 1359-4311/$ - see front matter Ó 2006 Elsevier Ltd. All rights reserved. doi:10.1016/j.applthermaleng.2006.06.012 * Corresponding author. Tel.: +90 312 212 68 20/1873; 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/apthermeng Applied Thermal Engineering 27 (2007) 481–491