Gear misalignment diagnosis using statistical features of vibration and airborne sound spectrums

Failure in gears, transmission shafts and drivetrains is very critical in machineries such as aircrafts and helicopters. Real time condition monitoring of these components, using predictive maintenance techniques is hence a proactive task. For effective power transmission and maximum service life, gears are required to remain in prefect alignment but this task is just beyond the bounds of possibility. These components are flexible, thus even if perfect alignment is achieved, random dynamic forces can cause shafts to bend causing gear misalignments. This paper investigates the change in energy levels and statistical parameters including Kurtosis and Skewness of gear mesh vibration and airborne sound signals when subjected to lateral and angular shaft misalignments. Novel regression models are proposed after validation that can be used to predict the degree and type of shaft misalignment, provided the relative change in signal RMS from an aligned condition to any misaligned condition is known.