Research on Mechanism/data Hybrid Modeling for Gas Turbine Performance Monitoring

Gas turbine has advantages of high efficiency, low emission, fast startup and shutdown, high energy density and so on, which is an important equipment in peak shaving of power grids and distributed energy systems. Gas turbine is always operated in a condition of high temperature, high pressure and high speed for a long time, and the risk of failure is high. Effective performance monitoring of gas turbine has become one of the most important research topics in the field of gas turbine operation and maintenance. In order to achieve the effective monitoring of gas turbine performance, it is necessary to establish an accurate model which can provide a real mechanism explanation for gas turbine. In this study, we use a method of combining mechanism and operation data to make the model closer to the reality and solve the problem of limited field operation data, based on the analysis of gas turbine mechanism and power plant operation data. A gas turbine mechanism/data hybrid model is established and verified with the power plant operation data of a typical M701F gas turbine. The results show that the model can accurately describe the performance of gas turbine within the relative error of 3% and can be used for the performance monitoring of gas turbine in power plant.