An aeroengine residual life prediction method based on multi-stage consistency check

Abstract

The invention discloses an aeroengine residual life prediction method based on multi-stage Wiener process consistency check. In the method, a statistical smoothing method smoothes engine performance monitoring data before and after maintenance. A heuristic segmentation algorithm performs performance degradation multi-stage partitioning; according to the multi-stage and randomness of engine performance degradation process, a performance degradation model is established by using multi-stage Wiener process. The consistency of the mean values of engine performance monitoring data before and aftermaintenance is checked by using the normal population mean consistency check method based on multi-stage Wiener process. According to the consistency test results of the degradation data before and after maintenance, it is decided whether the residual life prediction of the engine after maintenance fuses the monitoring data of the engine before maintenance, and the parameters of the multi-stage Wiener process are estimated by the monitoring data, and the residual life of the engine after maintenance is predicted. The method of the invention improves the accuracy of the model parameter estimation and the engine life prediction result, and has high practical value.

Description

technical field [0001] The invention relates to a method for predicting the remaining life of an aero-engine, in particular to a method for predicting the remaining life of an aero-engine based on a multi-stage Wiener process consistency test. Background technique [0002] Effectively predict the remaining life of aero-engines, and make corresponding maintenance and spare parts plans early on the basis of the prediction results, which can greatly reduce maintenance costs. In order to reduce the maintenance support costs of aero-engines and ensure the safety of aircraft operation, it is urgent to carry out relevant research on the prediction of the remaining life of aero-engines. [0003] The research directions of life prediction can be mainly divided into two categories: data-driven methods and physical failure models. The failure of the engine is the result of the gradual degradation of the material in the high temperature and high pressure environment. As various product...

AI Technical Summary

Problems solved by technology

[0004] However, the existing remaining life prediction methods of aero-engines do not take into account the multi-stage performance degradation and use the degradation monitoring data before maintenance for the remaining life prediction after maintenance, which makes the accuracy of the prediction results poor.

Images