A Preliminary Study for Aircraft Engine Health Management based on Multi-Scale Kalman Filters

Abstract

Aircraft engine is directly associated with flight safety. Its unpredicted failures lead to catastrophic accident and downtime. To prevent these problems, prediction of the accurate remaining useful life of engine is essential. With the rapid development of sensor technology, engine health condition can be monitored with multiple sensors. Therefore, it is important to develop suitable methodologies of integrating various data to improve the accuracy of remaining useful life. This paper attempts to establish fusion methods after examining the existing model based and data driven methods used for the remaining useful life estimation of gas turbine engine. The developed methods are evaluated using the simulated data set C-MAPSS, which includes the parameters associated with degradation in the fan, compressor and turbine during a series of flights.