Gear fault classification using Vibration and Acoustic Sensor Fusion: A Case Study

Abstract

Condition monitoring systems are increasingly being employed in industrial applications to improve the availability of equipment and to increase the overall equipment efficiency. Condition monitoring of gears, a key element of rotating machines, ensures to continuously reduce and eliminate costs, unscheduled downtime and unexpected breakdowns. Various gear fault diagnosis techniques have been reported which primarily focus on vibration analysis using statistical measures. On the other hand, acoustic signals possess a huge potential in condition monitoring, as acoustic monitoring is more sensitive to vibrating bodies than vibration sensors and hence provides an opportunity to identify faults in early stage. Still, limited studies have been reported for condition monitoring of rotating machines using acoustic sensing as compared to vibration sensing. The advantages of vibration based and acoustic based condition monitoring approaches may be synthesized by using sensor fusion, which is combining sensory data derived from different sources such that the resulting information has less uncertainty than the information derived from these sources individually. In the present work, classification of severity of chipped tooth fault in gears has been reported using vibration and acoustic sensor fusion and its effectiveness vis-vis vibration and acoustic approaches has been evaluated.