Hybrid Change Detection for Aircraft Engine Fault Diagnostics

Change detection is an important task for remote monitoring, fault diagnostics and system prognostics. When a fault occurs, it will often times cause changes in measurable quantities of the system. Early detection of changes in system measurements that indicate abnormal conditions helps the diagnostics of the fault so that appropriate maintenance action can be taken before the fault progresses, causes secondary damage to the system and the equipment experiences downtime. In this paper, we investigate the performance of a suite of change detection algorithms. A set of synthetic time series data with different change patterns are generated based on the empirical distribution of real engine performance data so that the individual change detection algorithm can be evaluated and compared against each other. At last, the results from the individual change detection algorithms are fused together to demonstrate that the ensemble of the change detection algorithms generates better performance than any individual detection algorithm.