Calculation of some exergetic indicators in a solar dryer and modeling with artificial neural network

Öz

Thermodynamic analysis, especially exergy analysis, is an important tool for analysis of thermal systems. Many formulations and data are used for exergy calculations in drying systems. Today, it is difficult to process and analyze a large amount of data manually. Therefore, in order to solve a given problem, it is aimed to reach the solution by educating the data obtained from the problem environment with artificial intelligence methods. In this study, apple product was dried in a solar drying system and exergy analysis of the drying process of the product was carried out. The effects of some exergetic indicators on the performance of drying system used in apple product drying were investigated. For this purpose, exergetic indicators such as exergy effect, waste exergy ratio, environmental impact factor, external sustainability index and improvement potential have been taken into consideration. A predictive model was constructed using the artificial neural network to estimate the waste exergy rate, which is an exergetic indicator.  Mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE) and root relative absolute error (RRAE) error analyzes were used to calculate the validity of the model. As a result, the waste exergy ratio increased as the drying time increased. Exergy efficiency and improvement potential of solar drying system decreased with increasing drying time. The predictive model created using ANN has successfully predicted the rate of waste exergy ratio. It has been shown that the resulting predictive model can be used for different drying systems and different products.

Anahtar Kelimeler

• Solar drying,Exergetic indicators,Waste exergy ratio,Artificial neural network

Güneş enerjili bir kurutucudaki ekserjetik faktörlerin hesaplanması ve yapay sinir ağı ile modellenmesi

Öz

Termodinamik analiz, özellikle ekserji analizi, termal sistemlerin analizi için önemli bir araçtır. Kurutma sistemlerinde ekserji hesaplamaları için birçok formülasyon ve veri kullanılmaktadır. Bugün, büyük miktarda veriyi elle işlemek ve analiz etmek zordur. Bu nedenle, verilen bir problemi çözmek için problem ortamından elde edilen verileri yapay zeka yöntemleri ile eğiterek çözüme ulaşmak hedeflenmektedir. Bu çalışmada, elma ürünü bir güneş kurutma sisteminde kurutuldu ve ürünün kurutma işleminin ekserji analizi yapıldı. Bazı ekserjetik faktörlerin elma ürünü kurutmasında kullanılan kurutma sisteminin performansı üzerine etkileri incelenmiştir. Bu amaçla, ekserji etkisi, atık ekserji oranı (AEO), çevresel etki faktörü (ÇEF), ekserjetik sürdürülebilirlik indeksi (ESI) ve iyileştirme potansiyeli (IP) gibi ekserjetik faktörler dikkate alınmıştır. Eksergetik bir faktör olan AEO değerlerini tahmin etmek için yapay sinir ağı kullanılarak öngörücü bir model oluşturulmuştur. Modelin geçerliliğini hesaplamak için ortalama mutlak hata (MAE), kök ortalama kare hatası (RMSE), göreceli mutlak hata (RAE) ve kök göreceli mutlak hata (RRAE) hata analizleri kullanılmıştır. Sonuç olarak, kuruma süresi arttıkça AEO artmıştır. Güneş enerjisi kurutma sisteminin ekserji verimliliği ve gelişme potansiyeli, kuruma süresi arttıkça azalmıştır. YSA kullanılarak oluşturulan öngörücü model, AEO değerlerini başarıyla öngörmüştür. Elde edilen öngörü modelinin farklı kurutma sistemleri ve farklı ürünler için kullanılabileceği gösterilmiştir.

Anahtar Kelimeler

• Güneş kurutucu,Ekserjetik faktörler,Atık ekserji oranı,Yapay sinir ağı

Kaynakça

1. Aghbashlo, M., Mobli, H., Rafiee, S., Madadlou, A. (2012). The use of artificial neural network to predict exergetic performance of spray drying process: A preliminary study. Computers and Electronics in Agriculture, 88, 32-43.
2. Akpinar E.K., (2010). Drying of mint leaves in a solar dryer and under open sun: modelling, performance analyses. Energy Convers Manag 51:2407-2418.
3. Bilgiç, Y., Yildiz, C., (2017). Güneş enerjili bir damıtıcıda emici yüzey alanının ekserji verimi üzerindeki etkisinin deneysel olarak incelenmesi. DÜMF Mühendislik Dergisi, 8(1), 191-202.
4. Bilgili, M., Sahin, B. ve Yasar, A., (2007). Application of Artificial Neural Networks for the Wind Speed Prediction of Target Station Using Reference Stations Data, Renewable Energy 32, 2350-2360.
5. Biswas, S., Chandra, S., Ghosh, I., (2017). Estimation of Vehicular Speed and Passenger Car Equivalent Under Mixed Traffic Condition Using Artificial Neural Network. Arabian Journal for Science and Engineering, 42(9), 4099-4110.
6. Bulut, H., Boloğur, H., Beyazıt, N. İ., Demirtaş, Y. and İşıker, Y., (2017). Design and Experimental Analysis of A Solar Hybrid Type Drying System, International Advanced Researches & Engineering Congress, Osmaniye, 16-18 Kasım, s.1-9.
7. Eslamian, S. S., Gohari, S. A., Zareian, M. J., Firoozfar, A., (2012). Estimating Penman–Monteith reference evapotranspiration using artificial neural networks and genetic algorithm: a case study. Arabian Journal for Science and Engineering, 37(4), 935-944.
8. Fudholi, A., Sopian, K., Alghoul, M. A., Ruslan, M. H., Othman, M.Y., (2015). Performances and improvement potential of solar drying system for palm oil fronds. Renewable Energy, 78, 561-565.

9. Fudholi, A., Sopian, K., Othman, M. Y., Ruslan, M. H., Bakhtyar, B., (2013). Energy analysis and improvement potential of finned double-pass solar collector. Energy Conversion and Management, 75, 234-240.
10. Ghritlahre, H. K., Prasad, R. K., (2018). Exergetic Performance Prediction of a Roughened Solar Air Heater Using Artificial Neural Network. Strojniski Vestnik/Journal of Mechanical Engineering, 64(3).
11. Gill, J., Singh, J., (2017). Energetic and exergetic performance analysis of the vapor compression refrigeration system using adaptive neuro-fuzzy inference system approach. Experimental Thermal and Fluid Science, 88, 246-260.
12. Gong, M. ve Wall, G., (2001). On Exergy and Sustainable Development-Part 2: Indicators and Methods, International Journal of Exergy, 1, 4, 217-231.
13. Ibrahim, A., Fudholi, A., Sopian, K., Othman, M.Y., Ruslan, M. H., (2014). Efficiencies and improvement potential of building integrated photovoltaic thermal (BIPVT) system. Energy Conversion and Management, 77, 527-534.
14. Mekhilef, S., Safari, A., Mustaffa, WES., Saidur, R., Omar R. and Younis MAA., (2012). Solar energy in Malaysia: current state and prospects, Renew Sustain Energy Rev., 16(1):386–96.
15. Midilli A, Kucuk H., (2015). Assessment of exergetic sustainability indicators for a single layer solar drying system. Int J Exergy 16(3):278–292.
16. Morosuk, T., Tsatsaronis, G., Schult, M., (2013). Conventional and advanced exergetic analyses: theory and application. Arabian Journal for Science and Engineering, 38(2), 395-404.
17. Orhan, M. F., Dincer, I., Rosen, M. A., (2009). Energy and exergy analyses of the drying step of a copper-chlorine thermochemical cycle for hydrogen production. International Journal of Exergy, 6(6), 793-808.
18. Osuolale, F. N., Zhang, J., (2018). Exergetic Optimisation of Atmospheric and Vacuum Distillation System Based on Bootstrap Aggregated Neural Network Models. In Exergy for A Better Environment and Improved Sustainability 1 (pp. 1033-1046). Springer, Cham.
19. Rivero, R., (2002). Application of the Exergy Concept in the Petroleum Refining and Petrochemical Industry, Energy Conversion and Management, 43, 1199-1220.
20. Song, T. W., Sohn, J. L., Kim, J. H., Kim, T. S. ve Ro, S. T., (2002).Exergy-Based Performance Analysis of the Heavy-Duty Gas Turbine in Part-Load Operating Conditions, International Journal of Exergy, 2,105-112.
21. Valencia, G. E., Restrepo, J. B., Osorio, M., (2018). Exergetic Modelling of a 30-kW Gas Microturbine and Cogeneration System by Artificial Neural Networks. Chemical Engineering Transactions, 70, 1873-1878.
22. Van Gool, W., (1997).Energy Policy: Fairly Tales and Factualities. In Innovation and Technology.
23. Zisopoulos, F.K., Rossier-Miranda F.J., Goot A.J.V.D, Boom R.M., (2017). The use of exergetic indicators in the food industry – A review. Critical Reviews in Food Science and Nutrition 57(1):197-211.