Aero-engine continuous health state evaluation method based on SAE-HMM

Abstract

The invention discloses an aero-engine continuous health state evaluation method based on SAE-HMM, and the method comprises the steps: collecting aero-engine monitoring parameters; preprocessing parameters; carrying out SAE model feature extraction; dividing health states; enabling the HMM model to describe a probability corresponding relation and a probability transition relation between the parameters and the health state; training a hidden Markov model according to the historical parameter data; monitoring parameter data in real time, performing health state evaluation through the established SAE-HMM model; calculating the current health degree of the engine according to the state probability values output by the SAE-HMM model, and carrying out the early warning of the health state transition of the engine. According to the method, while the original information amount is guaranteed, the method has the self-adaptive capacity of being high in model operation efficiency, low in complexity and capable of supporting uncertain dimension parameters and characteristics, the engine continuous degradation rule contained in the multi-dimensional data is effectively mined and represented,the engine health state evaluation precision is improved, and more accurate state transition early warning is achieved.

Description

technical field [0001] The invention relates to the field of aero-engines, in particular to an SAE-HMM-based continuous health state assessment method for aero-engines. Background technique [0002] In recent years, modern aerospace technology has continued to improve, and aviation vehicles have entered more and more fields, and their flight capabilities have also been continuously enhanced. With the improvement of the performance of aviation aircraft, people have higher and higher requirements for its safety and reliability. As the main power source and the most important part of the aircraft, the failure of the aero-engine often results in the destruction of the aircraft and fatalities. At the same time, the stability of the engine is often difficult to control due to many factors such as high integration among its components, harsh working environment, and very complicated composition structure. [0003] At present, there are mainly two types of health status assessment...

AI Technical Summary

Problems solved by technology

At the same time, due to many factors such as the high degree of integration between its components, the harsh working environment, and the complex structure, the stability of the engine is often difficult to control.

[0003] At present, there are mainly two types of health status assessments for aero-engines. One is regular inspections and repairs. After specified sorties, engine inspections and repairs are carried out. Although this can also serve as an assessment of the health status, However, it lacks real-time performance and consumes a lot of manpower and material resources; the second is post-failure maintenance, but this is an inappropriate means after a fault or abnormality occurs, and it is difficult to play an early warning role

Images