Exergy analysis of a cogeneration system through Artificial Neural Network (ANN) method


Yoru Y., KARAKOÇ T. H., Hepbasli A.

INTERNATIONAL JOURNAL OF EXERGY, cilt.7, sa.2, ss.178-192, 2010 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 7 Sayı: 2
  • Basım Tarihi: 2010
  • Doi Numarası: 10.1504/ijex.2010.031239
  • Dergi Adı: INTERNATIONAL JOURNAL OF EXERGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.178-192
  • Anahtar Kelimeler: cogeneration, exergy, ANN, artificial neural network, gas turbine, spray dryer, FANN, fast artificial neural network, HEAT, CYCLE
  • Anadolu Üniversitesi Adresli: Hayır

Özet

The main objective of this study is to apply the Artificial Neural Network (ANN) method to a cogeneration system, located in Izmir, Turkey, for exergetic evaluation purposes. The data used are based on the actual operational conditions and the results obtained from this system, which was exergetically analysed by the authors. It consists of three turbines with a total capacity of 13 MW, six spray dryers and two heat exchangers. A comparison between the exergy destruction values obtained from exergy analysis calculations and the ANN method is made. Fast ANN (FANN) package (library) has been chosen as an ANN application to implement into the C++ code named CogeNNExT, which has been written and developed by the authors. From the single output of the ANN (FANN) results, the main exergy destruction rate with 60.96 MW in the exergetic analysis is found to be 61,001 MW with an error of 0.075%. From the two outputs of another ANN result, the mean input and output exergy values are found with errors of 0.438% and 2.211%, respectively.