Artificial Neural Network Based Performance prediction of Exergy and Energy Analysis of Gas Turbine Generator using Cycle-Tempo Software

Abstract

It is crucial for research to continuously seek innovative methods of generating additional electricity in order to meet the demands of everyone requiring it. Engineers can work to make the companies that provide electricity better. It is not possible to separate the parts of the system from how well the gas turbine generator works. This research introduces a new method to predict the performance of Gas Turbine Generators (GTGs) using Artificial Neural Networks (ANNs) combined with Cycle-Tempo software. The main emphasis of this method is on analysing the exergy and energy of the GTGs. GTGs are very important in many different industries. It is crucial to make them work efficiently to produce more energy and protect the environment. This research is new and different because it uses ANNs in a smart way to improve how research measure how well GTG works. The main advancement is in the automation part, where artificial neural networks are taught to independently collect and study data. They can adjust to changing conditions on their own, which greatly reduces the amount of manual work needed for analysis. This automation makes things easier and can change to different situations quickly. It helps industries that rely on GTG by meeting their changing needs. Moreover, the research uses complex computer algorithms to make very accurate forecasts about energy and exergy effectiveness, voltage output, and hydrogen production—an important measurement in GTG function. The results show that the accuracy is really good, with a small error of less than 1% and a high value of 0. 99 for the R-squared when compared to what was expected. The automation, detailed analysis, and accurate predictions of the novel technology help improve the efficiency and sustainability of gas turbine generators. This makes it a valuable tool for industries that rely on these generators for power.