Developing Sensors and Instrumentation for Smart Turbines

Real-Time Health Monitoring of Gas Turbine Components Using Online Learning and High-Dimensional Data 

Department of Energy – University Turbine Systems Research Program

​This project leverages data analytics to address challenges surrounding “Big Data” sets. Data analytics associated with big data offers unique capabilities to gas turbine operation through its ability to synthesize information from physical sensors and infer additional information from “virtual” sensors. By utilizing engine-representative and engine-feasible sensor technologies to observe seeded faults, multiple high-fidelity data sets have been generated for predictive algorithm development.

Using these data sets, predictive algorithms for purge flow sealing performance (ε) and blade-film cooling flow have been generated. These parameters, which are critical to the health and longevity of critical turbine hardware, cannot be directly measured in the engine. By applying the models developed through this project, engine manufacturers and operators can estimate accumulated degradation, remaining useful life, and the root cause of incipient faults.