Health condition prognostics of gears using a recurrent neural network approach

The development of accurate health condition prediction approaches has been a key research topic in condition based maintenance (CBM) in recent years. However, current health condition prediction approaches are not accurate enough, which has become the bottleneck for achieving the full power of CBM. In this work, we develop a recurrent neural network approach for equipment health condition prediction. The effectiveness of the approach is illustrated using data collected from a lab gearbox experimental system.