Abstract
As the main power source for aircrafts, the reliability of an aero engine is critical for ensuring the safety of aircrafts. Prognostics and health management (PHM) on an aero engine can not only improve its safety, maintenance strategy and availability, but also reduce its operation and maintenance costs. Residual useful life (RUL) estimation is a key technology in the research of PHM. According to monitored performance data from the engine’s different positions, how to estimate RUL of an aircraft engine by utilizing these data is a challenge for ensuring the engine integrity and safety. In this paper, a framework for RUL estimation of an aircraft engine is proposed by using the whole lifecycle data and performance-deteriorated parameter data without failures based on the theory of similarity and supporting vector machine (SVM). Moreover, a new state of health indicator is introduced for the aircraft engine based on the preprocessing of raw data. Finally, the proposed method is validated by using 2008 PHM data challenge competition data, which shows its effectiveness and practicality.
Highlights
Recent developments of complex systems, such as aircraft engines, engineering machines, high-speed vehicles and computer numerical control (CNC) systems have been emphasized by the increasing requirements of on-line health monitoring for the purpose of maximizing its operational reliability and safety [1,2,3]
The data are extracted from the same data sets as the previous case, but these whole life data of the original samples are cut from the same data sets as the previous case, but these whole life data of the original samples are cut off the rear part partand andonly onlythe thefront frontpart part data applied in this scheme
This paper presents two schemes to estimate the residual useful life (RUL) of an aircraft engine under different situations
Summary
Recent developments of complex systems, such as aircraft engines, engineering machines, high-speed vehicles and computer numerical control (CNC) systems have been emphasized by the increasing requirements of on-line health monitoring for the purpose of maximizing its operational reliability and safety [1,2,3]. Developed a similarity-based to predict the RUL by data comparing evolution systems normally needed, but it is difficult approach to obtain enough run-to-failure for the its long-life data to the trajectory patterns of reference samples through fuzzy similarity analysis, and aggregating systems with high reliability. If there are more reference systems similar to than the its it is reasonable to assign more weight to a system’s most recent sampling point researched one, point the similarity-based approach can be introduced through a weighted average the earlier sampling of performance parameters when measuring its similarity with otherofsystems. This paper attempts to develop a modified similarity and SVM-based method to predict the RUL of an aircraft engine, including two schemes with different reference samples.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
