Heavy duty gas turbine engines are not only ingesting the air, but also eating a myriad of aerosol particles, which may have various negative effects on the turbine operation efficiency as well as the component failure. This paper attempts to develop predictive degradation models for gas turbines by integrating satellite collected atmospheric factors, on-site monitoring data, and physics-based calculated performance results. Multiple variables are analyzed and employed for predictive modeling. The vital variables are identified by using data exploratory correlation analysis and stepwise regression analysis. The performance degradation calculation is obtained from physics based thermodynamic heat balance of gas turbine. It requires balancing mass and energy of gas turbine to match measurement data through thermodynamic cycle matching. The performance degradation prior to the offline water wash is used as the predictor. Artificial neural network modeling is employed to establish the predictive models. A procedure is presented to explain the proposed methodology, and results are discussed. This paper provides an effective methodology and procedure to apply big data for the performance degradation prediction of gas turbines.
Read full abstract