ACTIONABLE MAINTENANCE INFORMATION FROM HUMS

摘要

Condition Based Maintenance (CBM) of military helicopters is tracked by Condition Indicators (CI) calculated from Health Usage and Monitoring Systems (HUMS) vibration sensors. Even though many CIs have been proposed and implemented, they remain highly variable and difficult to interpret, leading maintainers to become desensitized. Here we show that a sequential Monte Carlo algorithm operating a stochastic non-linear model that includes a description of fault evolution can circumvent the fundamental shortcoming of the CI approach. We estimate fault probabilities from vibration spectra time-histories, showing excellent artifact rejection and accurate fault detections several months prior to all other existing warnings. We expect this approach may eventually allow scheduled maintenance to substitute unscheduled downtime, reducing maintenance cost.