Multisensor monitoring of gear tooth fatigue for predictive diagnostics

Abstract

AbstractSuccessful machinery diagnostics depends on the collection and processing of prognostic features that relate back to failure precursors. Since gear teeth are a critical element in drive‐train systems, single gear tooth failure has been examined, and the identification of new prognostic features explored. A special jig was employed to orient and constrain gear samples while Hertzian loading was applied along a single contact line on the gear tooth face. This set‐up simulates the loading conditions experienced by a single tooth during gear train operation. Optical, ultrasonic, and mechanical sensors measured a variety of observables while the gear fatigue testing was under way. After monitoring the fatigue test with these three non‐commensurate sensors, data features were related to crack growth phenomena. Data collection, analysis, and interpretation are discussed for spur gear samples that show both the absence and presence of cracks and support the validity of the identified features as failure precursors. The results demonstrate the potential for using non‐traditional sensors and techniques for an in situ monitoring system.