Exergetic Analysis of a Natural Gas Combined-Cycle Power Plant with a Molten Carbonate Fuel Cell for Carbon Capture

This study aims to propose the repowering of an existing Italian natural-gas fired combined cycle power plant through the integration of Molten Carbonate Fuel Cells (MCFC) downstream of the gas turbine for CO2 capture and to pursuit an exergetic analysis of the two schemes. The flue gases of the turbine are used to feed the cathode of the MCFC, where CO2 is captured and transported to the anode while generating electric power. The retrofitted plant produces 787.454 MW, in particular, 435.29 MW from the gas turbine, 248.9 MW from the steam cycle, and 135.283 MW from the MCFC. Around 42.4% of the exergy destruction has been obtained, the majority belonging to the combustion chamber and, in minor percentages, to the gas turbine and the MCFC. The overall net plant efficiency and net exergy efficiency are estimated to be around 55.34 and 53.34%, respectively. Finally, the specific CO2 emission is around 66.67 kg/MWh, with around 2 million tons of carbon dioxide sequestrated.

Power Prediction of Combined Cycle Power Plant (CCPP) Using Machine Learning Algorithm-Based Paradigm

Power prediction is important not only for the smooth and economic operation of a combined cycle power plant (CCPP) but also to avoid technical issues such as power outages. In this work, we propose to utilize machine learning algorithms to predict the hourly-based electrical power generated by a CCPP. For this, the generated power is considered a function of four fundamental parameters which are relative humidity, atmospheric pressure, ambient temperature, and exhaust vacuum. The measurements of these parameters and their yielded output power are used to train and test the machine learning models. The dataset for the proposed research is gathered over a period of six years and taken from a standard and publicly available machine learning repository. The utilized machine algorithms are K -nearest neighbors (KNN), gradient-boosted regression tree (GBRT), linear regression (LR), artificial neural network (ANN), and deep neural network (DNN). We report state-of-the-art performance where GBRT outperforms not only the utilized algorithms but also all the previous methods on the given CCPP dataset. It achieves the minimum values of root mean square error (RMSE) of 2.58 and absolute error (AE) of 1.85.