Gas path fault diagnosis method and system for dynamic process of aeroengine

Abstract

The invention discloses a gas path fault diagnosis method and system for the dynamic process of an aero-engine. The method includes: establishing a feature extraction model based on a multi-layer kernel extreme learning machine; using a time-series modeling-based hidden Markov model for fault identification . The present invention solves the problem of low accuracy of conventional data-based engine fault diagnosis using time-series measurement data in the existing dynamic process of aeroengine gas circuit fault diagnosis, and is suitable for considering the degradation of gas circuit components and sensor parameters The dynamic fault diagnosis of the engine in the case of redundancy plays a positive role in promoting engine health management and reducing maintenance costs.

Description

technical field

[0001] The invention belongs to the field of air path fault diagnosis of aero-engines, and in particular relates to a gas path fault diagnosis method and system for the dynamic process of an aero-engine. Background technique

[0002] As the heart of an aircraft, an aero-engine has a complex structure and a harsh working environment. Engine fault diagnosis technology is an important means to ensure engine performance and reliability and reduce maintenance costs. During the service of an aero-engine, the performance of components will slowly degrade. In addition, sudden changes in component health parameters may occur; at the same time, due to the harsh working environment, sensors are also one of the components that are prone to failure; gas circuit component failure and sensor failure Together affect the performance and reliability of aero-engines, it is necessary to diagnose them.

[0003] At present, the fault diagnosis of aeroengine air circuit components...

Images