Multivariable support vector machine prediction method for aero-engine rotor residual life

Abstract

The invention provides a multivariable support vector machine prediction method for aero-engine rotor residual life. According to the method, service time, a load spectrum, rotation speed and vibration signal characteristics of an aero-engine rotor are selected to be as input parameters of a life prediction model. A multivariable support vector machine prediction model for the residual life is established based on a multivariable prediction method, sample parameters are input to the model to be trained and then output, and prediction for the residual life of the aero-engine rotor is achieved under a small sample condition. The method is simple and practical, reliable in result, good in instantaneity and is suitable for quantitatively calculating the residual life of the aero-engine rotor under the small sample condition.

Description

technical field [0001] The invention belongs to the field of life prediction, and in particular relates to a multivariate support vector machine prediction method for the remaining life of an aeroengine rotor. Background technique [0002] At present, all countries and major airlines in the world attach great importance to the research of aero-engine safety technology. Various models of Boeing and Airbus aircraft are equipped with a complete condition monitoring and fault diagnosis system, with an average of 15 monitoring parameters. Although condition monitoring and fault diagnosis systems are relatively common in the analysis of aero-engines, in-flight parking accidents caused by fatigue cracks and bearing failures have emerged in an endless stream. Therefore, in-depth research on the expansion of rotor cracks and the realization of rotor condition monitoring and remaining life prediction can lay a solid theoretical foundation for improving the safety and reliability of a...

AI Technical Summary

Problems solved by technology

When studying a certain phenomenon or predicting a certain change, it is necessary to observe and record multiple indicators at the same time, and comprehensively predict the development of the whole thing according to the change law of multiple variables and the interdependence between variables. However, the traditional multivariate forecasting method deals with small The problem of forecasting under sample conditions still has some difficulties

The service conditions of aero-engine rotors are complex, and its fatigue damage is a problem affected by various factors, and it becomes a small-sample problem due to the limitations of long test period and high cost. Therefore, it is necessary to develop a life prediction method for aero-engines

Images