Aero-engine fault diagnosis method and system and electronic equipment

Abstract

The invention relates to an aero-engine fault diagnosis method and system and electronic equipment, and the method comprises the steps: making two-time analysis of the parameters of a to-be-diagnosed aero-engine, and specifically employing at least three types of analysis methods to analyze the parameters of the to-be-diagnosed aero-engine, adopting at least three correlation coefficient algorithms to analyze every two sensitive parameters in the first sensitive parameter union set; through fusion of multiple methods, fully mining association information between parameters, creating an association relationship between a fault mode and the parameters to provide information support for fault diagnosis; and on the basis, making fault diagnosis on the aero-engine to be diagnosed through the fault diagnosis model to obtain an accurate fault diagnosis result, so that fault elimination is carried out on the basis of the fault diagnosis result, inestimable loss caused by further serious faults is avoided, and the operation safety of the aircraft is ensured. And the investment of maintenance cost can be reduced to a great extent.

Description

technical field [0001] The invention relates to the technical field of aeroengines, in particular to an aeroengine fault diagnosis method, system and electronic equipment. Background technique [0002] As the "heart" of the aircraft, the aero engine is self-evident. Aeroengines have a very complex structure, and they are often under very harsh working conditions such as high temperature, high pressure, and high speed, so they are prone to various unknown failures. As the core equipment of the aircraft, its failures often cause immeasurable losses. Through the fault diagnosis of the key components of the aero-engine, the faults can be easily eliminated, which can avoid major faults caused by faults and incalculable losses, reduce maintenance costs, and ensure the healthy and stable operation of the aero-engine. [0003] Traditional aero-engine fault diagnosis methods mainly include model-based methods and data-driven methods, specifically: [0004] 1) The model-based engin...

AI Technical Summary

Problems solved by technology

[0004] 1) The model-based engine fault diagnosis method needs to establish a complex aeroengine model, which relies on expert knowledge, and the diagnosis results largely depend on the accuracy of the established mathematical model, but there are still problems such as low training efficiency and poor accuracy

[0005] 2) Based on the data-driven method, mainly using artificial feature extraction + classification model mode, it is necessary to combine a large amount of prior knowledge, select and design appropriate feature parameters from a large amount of monitoring data, the implementation cost is high, and the diagnostic accuracy depends on manually extracted features accuracy and effectiveness; when diagnosing different key components of an aero-engine, it is necessary to build models or extract features separately, which is complicated and inefficient

Images