APPLICATION OF ARTIFICIAL NEURAL NETWORK (ANN) METHOD TO EXERGETIC ANALYSES OF GAS TURBINES

摘要

In this study, ANN method is applied to exergetic analyses of gas turbines (GT) by using actual operating data of 3 GTs. These 3 GTs are operating to supply heat and power in a cogeneration system of a ceramic factory, located in Izmir, Turkey. 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. After assuming which inputs of GTs are needed, comparisons between the exergy values obtained from exergy analysis and the exergy values obtained from ANN method are made. In these compressions, cross tests are also applied. In an example ANN trained by data of first GT and using this trained data, ANN exergy results are calculated and compared by actual second GT results. All of the results of exergetic analysis of GTs are compared and shown by graphics. As a result of analysis, ANN is successfully applied to obtain exergetic results of GTs. These are shown by graphics including input, output, fuel, product exergies and exergy destruction results of GTs. RMSE (Root Mean Square Error) values are found under 0.01 which means that data set including inputs and outputs of many GTs would be perfect to obtain much closer exergetic results by an ANN.