Abstract
In the turbine section of a modern gas turbine engine, components exposed to the main gas path flow rely on cooling air to maintain hardware durability targets. Therefore, monitoring turbine cooling flow is essential to the diagnostic and prognostic efficacy of a condition-based operation and maintenance (CBOM) approach. This study supports CBOM goals by leveraging supervised machine learning to estimate relative changes to local film-cooling flow rate using surface temperature measured on the pressure side of a rotating turbine blade operating at engine-relevant aerothermal conditions. Throughout the lifetime of a film-cooled turbine component, characteristics of the film-cooling flow — such as film trajectory and cooling effectiveness — vary as degradation-driven geometry distortions occur, which ultimately affects the relationship between the model input and the model output – film-cooling flow rate predictions. The present study addresses this complication by testing a data-driven model on multiple turbine blades of the same nominal design, but with each blade exhibiting different localized film-cooling flow characteristics. By testing the model in this manner, strategies for mitigating the detrimental effects of film-cooling flow characteristic variations on model performance were investigated, and the corresponding flow rate prediction accuracy was quantified.
