Prediction Interval Estimation of Aeroengine Remaining Useful Life Based on Bidirectional Long Short-Term Memory Network

Reliable and accurate aero-engine remaining useful life (RUL) prediction plays a key role in aero-engine prognostics and health management (PHM) system. However, due to the epistemic uncertainties associated with aero-engine systems, prediction errors are unavoidable and sometimes significant in traditional deterministic point prediction methods. To improve the accuracy and credibility of RUL prediction, a novel prediction interval (PI) estimation method is proposed to quantify the uncertainties in RUL prediction. The proposed method involves the data clustering, mathematical statistical analysis and deep learning techniques, and is achieved through offline and online phases. In the offline phase, an enhanced fuzzy c-means algorithm (FCM) is proposed to divide the aero-engine health status into several discrete states. After labeling the health state of each sampling point, PIs are computed for them. This step is achieved by the empirical distributions of errors associated with all instances belonging to the health state under consideration. In the online phase, a bidirectional long short-term memory (Bi-LSTM) network is employed to estimate the boundaries of point prediction, and thus the PI of aero-engine RUL is generated. The aero-engine degradation dataset from NASA is used to validate the proposed RUL PI estimation method. The results obtained indicate that the proposed method is a promising tool for providing reliable aero-engine RUL interval estimates, which can inform maintenance-related decisions.