Long-Term NOx Emission Behavior of Heavy Duty Gas Turbines: An Approach for Model-Based Monitoring and Diagnostics

Abstract

Accurate monitoring of gas turbine performance is a means to an early detection of performance deviation from the design point and thus to an optimized operational control. In this process, the diagnosis of the combustion process is of high importance due to strict legal pollution limits as aging of the combustor during operation may lead to an observed progression of NOx emissions. The method presented here features a semi-empirical NOx formulation incorporating aging for the GT24/GT26 heavy duty gas turbines: Input parameters to the NOx-correlation are processed from actual measurement data in a simplified gas turbine model. Component deterioration is accounted for by linking changes in air flow distribution and control parameters to specific operational measurements of the gas turbine. The method was validated on three different gas turbines of the GE GT24/GT26 fleet for part- and baseload operation with a total of 374,058 long-term data points (5 min average), corresponding to a total of 8.5 years of observation, while only commissioning data were used for the formulation of the NOx correlation. When input parameters to the correlation are adapted for aging, the NOx prediction outperforms the benchmark prediction method without aging by 35.9, 53.7, and 26.2% in terms of root mean square error (RMSE) yielding a root-mean-squared error of 1.27, 1.84, and 3.01 ppm for the investigated gas turbines over a three-year monitoring period.

Tabular Machine Learning Methods for Predicting Gas Turbine Emissions

“…They combined different datasets, such as validation measurements and long-term operational data, to provide more meaningful emission trends. Lipperheide et al [11] also incorporated ageing of the gas turbines into their analytical model, which is capable of accurately predicting NOx emissions for power in the range of 60-100%. Siemens Energy developed a Chemical Kinetics model [7] to accurately predict CO and NOx emissions for their SGT-400 gas turbine.…”

Aero-Engine Real-Time Models and Their Applications

“…In modelbased surge margin control, surge margin control loop is added to the controller structure due to the virtual measurement data obtained by the real-time model, which directly limits the surge margin and greatly improves the engine dynamic performance during acceleration process. ese years, model-based control methods have been applied to more and more fields, such as NOx emissions monitoring [82] and engine start-up optimization [83]. It can be ensured that real-time model will play a more and more important role in advanced FADEC system in the future.…”