An Interval-Valued Prediction Method for Remaining Useful Life of Aero Engine

Aero engine is the core power unit of aircraft. A satisfactory prediction of remaining useful life (RUL) for an aero engine can ensure timely replacement and maintenance of engine and can avoid huge loss caused by engine failure during flight mission. In this paper, a multi-layer perceptron (MLP) pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Bingce, Wang, Degang, Song, Wenyan, Zhang, Shuo, Lin, Sida
Format: Conference Proceeding
Language:English
Subjects:
Aero engine
Degradation
Engines
interval information granule
Maintenance engineering
Neurons
Numerical models
Predictive models
Principal component analysis
remaining useful life
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aero engine is the core power unit of aircraft. A satisfactory prediction of remaining useful life (RUL) for an aero engine can ensure timely replacement and maintenance of engine and can avoid huge loss caused by engine failure during flight mission. In this paper, a multi-layer perceptron (MLP) prediction model based on information granular theory is proposed to estimate the RUL interval of aero engine. Firstly, the principal component analysis (PCA) method is considered to reduce dimension of inputs due to large number of sensor measurements of aero engines. Then a method to find the degradation interval of engine by the principle of justifiable granularity is designed, and the expected maximum RUL of each engine can be determined dynamically. Furthermore, a multi-layer perceptron is used to find the relation between aero engine sensor measurements and remaining useful life, by which the RUL interval of aero engine is obtained. Some numerical simulations show that the proposed model can obtain satisfactory performance.
ISSN:2161-2927
DOI:10.23919/CCC50068.2020.9189621