Aircraft engine residual life prediction method based on deep learning coupling modeling

Abstract

The invention relates to an aircraft engine residual life prediction method based on deep learning coupling modeling, and the method comprises the steps of obtaining a multi-element sensor failure signal of an aircraft engine, loading the multi-element sensor failure signal into a deep learning coupling model, obtaining the potential failure state distribution of the aircraft engine along with the time evolution, obtaining the distribution result of the residual service life, and thus realizing residual life prediction of the aircraft engine; the deep learning coupling model comprises a failure process model and a fusion model, the failure process model is used for describing the potential failure state of the aircraft engine along with time evolution, and the fusion model is used for constructing the health index HI of the engine in combination with multi-element sensor failure signals. Compared with the prior art, the invention has the advantages that the failure process state of the aircraft engine is fully considered, and modeling of the failure process of the aircraft engine and prediction of the residual life of the aircraft engine are realized by utilizing multi-element sensor signal data which are acquired during operation of the aircraft engine and reflect the health state of the aircraft engine.

Description

technical field [0001] The invention relates to the technical field of aircraft engine remaining life prediction, in particular to an aircraft engine remaining life prediction method based on deep learning coupled modeling. Background technique [0002] The aircraft engine plays a vital role in the operation of the aircraft. If the engine fails suddenly, it will cause a series of unpredictable problems such as flight delays, customer satisfaction reduction, and safety hazards, which will cause serious economic losses and even disastrous consequences. Aircraft engine remaining useful life prediction technology is widely used to diagnose and predict the operating conditions of aircraft engines by using information from sensor data and engineering domain knowledge to predict the remaining useful life of aircraft engines (Remaining Useful Lifetime, RUL). Maintenance plays a key role. [0003] In recent years, machine learning methods have shown great potential in solving the p...

AI Technical Summary

Problems solved by technology

However, such methods lack the intrinsic connection between the two steps, and cannot guarantee the fit of HI to the failure process model

Images