Abstract
As the core component and main power source for aircrafts, the reliability of an aero engine is vital for the security operation of aircrafts. Degradation tendency measurement on an engine can not only improve its safety, but effectively reduce the maintenance costs. In this paper, a hybrid method using multi-sensor data based on fast ensemble empirical mode decomposition permutation entropy (FEEMD-PE) and regularized extreme learning machine (RELM), systematically blending the signal processing technology and trend prediction approach, is proposed for aircraft engine degradation tendency measurement. Firstly, a synthesized degradation index was designed utilizing multi-sensor data and a data fusion technique to evaluate the degradation level of the engine unit. Secondly, in order to eliminate the irregular data fluctuation, FEEMD was employed to efficiently decompose the constructed degradation index series. Subsequently, considering the complexity of intrinsic mode functions (IMFs) obtained through sequence decomposition, a permutation entropy-based reconstruction strategy was innovatively developed to generate the refactored IMFs (RIMFs), which have stronger ability for describing the degradation states and contribute to improving the prediction accuracy. Finally, RIMFs were used as the inputs of the RELM model to measure the degradation tendency. The proposed method was applied to the degradation tendency measurement of aircraft engines. The results confirm the effectiveness and superiority of the proposed method, and it is more suitable for actual applications compared with other existing approaches.
Highlights
With the growing complexity of mechanical systems, such as aircraft engines, electricity-producing devices, and high-speed vehicles, the increasing requirements of online health monitoring based on distributed sensor networks have become a focal point for the purpose of stable and reliable operation [1,2,3,4]
A hybrid measurement method using multi-sensor data based on a permutation entropy reconstruction scheme and a regularized extreme learning machine (RELM) prediction model was proposed to forecast the degradation tendency of aircraft engines
A one-dimensional synthesized degradation index based on multi-dimensional sensor data was constructed to accurately indicate the extent of degradation
Summary
With the growing complexity of mechanical systems, such as aircraft engines, electricity-producing devices, and high-speed vehicles, the increasing requirements of online health monitoring based on distributed sensor networks have become a focal point for the purpose of stable and reliable operation [1,2,3,4]. Degradation tendency measurement is an important step for CBM, which can help discover abnormal operation conditions before faults occur, and is crucial for reducing failure rate and maintenance costs [12,13,14,15]. Due to the development of sensor technology and simulation techniques, the operation condition of complex aircraft engine systems can be continuously monitored, and various sensor data from different positions can be collected in real time [16,17,18]. Volponi first pointed out that the health condition of gas turbines can be characterized by the fuel flow rate [19]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
