Modeling of heavy-duty gas turbine based on machine learning algorithms

This paper investigates gas turbine modeling techniques based on machine learning algorithms. Utilizing polynomial regression (PR), K-Nearest Neighbor (KNN), decision trees (DT), and multi-layer perceptrons (MLP), it constructs models from one year's operational data from a power plant's heavy-duty gas turbine. Predictions encompass key parameters such as compressor outlet temperature, compressor outlet pressure, power, and turbine exhaust temperature. Experimental results demonstrate that the MLP algorithm achieves high prediction accuracy for compressor outlet temperature (MAPE: 0.112%), compressor outlet pressure (0.201%), power (0.421%), and turbine outlet temperature (0.070%), highlighting its effectiveness in gas turbine modeling.