Aero-engine reliability monitoring method based on mixed weibull distribution

Abstract

The invention relates to an aero-engine reliability monitoring method based on mixed weibull distribution, and the method comprises the following steps of extracting state monitoring information and performance degradation information of an aero-engine which is already replaced and repaired; extracting a relation between each monitoring parameter and the performance degradation of the aero-engine by utilizing a support vector method, and realizing the monitoring of the performance degradation value of a wing engine; utilizing a degradation model to describe the accumulated degradation volume of the aero-engine on the basis of the monitoring result of the real-time degradation value of the wing aero-engine; estimating a random parameter in a linear degradation model of the aero-engine, and determining the variation of the random parameter and the upper limit and the lower limit of the accumulated performance degradation volume of the aero-engine; establishing an aero-engine reliability monitoring model based on the dual-parameter mixed weibull distribution; utilizing a maximal likelihood method to give an expression of each parameter in the aero-engine reliability monitoring module; estimating hyper-parameters of the aero-engine reliability monitoring module based on the dual-parameter mixed weibull distribution; and calculating the reliability monitoring value of the aero-engine, and realizing the real-time and precise reliability monitoring of the aero-engine.

Description

technical field [0001] The invention relates to the reliability monitoring technology of aero-engines, especially in combination with the failure rules and operation characteristics of the aero-engines themselves, making full use of various state monitoring information and maintenance and inspection information, to perform real-time reliability evaluation of aero-engines, and to realize on-wing monitoring of aero-engines. Reliability monitoring to ensure the safety of aero-engine operation and improve operational efficiency. Background technique [0002] The reliability of aero-engines is the basis for ensuring flight safety. Real-time reliability monitoring makes it easy to track the reliability changes of aero-engines and take timely measures to avoid aero-engine failures. At present, some advanced foreign theories and technologies, such as Prognostics and Health Management (PHM), Condition Based Maintenance (CBM), extended condition based maintenance plus (CBM+), autonom...

AI Technical Summary

Problems solved by technology

[0003] Compared with traditional reliability assessment, reliability monitoring puts more emphasis on the "precise" and "real-time" understanding of the reliability level, which is a requirement that traditional reliability assessment methods cannot meet

At present, in the field of aero-engine reliability evaluation, the following methods are mainly used: one is reliability evaluation based on fault data. The characteristic of this method is that it ignores a large amount of available condition monitoring information, and it cannot realize "real-time"; the second is to rely on the online monitoring condition monitoring parameters to monitor and evaluate the performance degradation of aeroengines. This method is simple and convenient. Intuitive, and can achieve "real-time", the disadvantage is that there is no way to make full use of information from multiple sources, that is, "accuracy" cannot be achieved, so it can only provide reference for decision-making, but cannot provide basis for decision-making; the third is Information fusion and processing methods represented by proportional hazards models and artificial intelligence methods are characterized by making full use of information from multiple sources to improve the "accuracy" of predictions, but the shortcomings of these methods are also obvious, that is, they are all based on Statistical average effect, while improving accuracy, ignores the impact of risk

To sum up, the current reliability assessment methods are still unable to solve the "precision", "accuracy" and "real-time" and good risk control capabilities in reliability assessment.

Images