Based on the results of a successful Phase I and II SBIR program performed by Impact Technologies, a suite of Prognostics and Health Management (PHM) algorithms have been developed for detecting incipient faults in the critical bearings associated with aircraft gas turbine engines. The component-level prognostic approach is presented that utilizes available sensor information from vibration transducers, along with material-level component fatigue models to calculate remaining useful life for the engine’s critical components. Specifically, correlation between the sensed data and fatigue-based damage accumulation models were developed to provide remaining useful life assessments for life limited components. The combination of health monitoring data and model-based techniques provides a unique and knowledge rich capability that can be utilized throughout the bearings’s entire life, using model-based estimates when no diagnostic indicators are present and using the monitored vibration features at later stages when incipient failure indications are detectable, thus reducing the uncertainty in model-based predictions. A description and specific implementation of this prognosis approach with application to high speed bearings is illustrated herein, using gas turbine engine and bearing test rig data as validation for the methods.
Prognostics and Health Management for Complex system Based on Fusion of Model-based approach and Data-driven approach
