Aero-engine degradation state fault diagnosis method based on transfer learning

Abstract

The invention provides an aero-engine degradation state fault diagnosis method based on transfer learning, and the method is realized based on an extreme learning machine (ELM), and the thought of transfer learning is added into the method. According to the method, a large amount of operation data when an engine is not degraded and a small amount of data of the engine in a certain degradation state are utilized, the data when the engine is not degraded are regarded as source domain data, and the degraded data are regarded as target domain data. The method is divided into two stages, in the first stage, data of a source domain is adopted to train an extreme learning machine model, and information of the source domain is extracted; in the second stage, target domain data is adopted for training, and the target domain is adapted. The aero-engine fault diagnosis method solves the problem of lack of aero-engine fault diagnosis data through transfer learning, combines the aero-engine fault diagnosis data with ELM, and ensures the real-time performance and accuracy of fault diagnosis.

Description

technical field [0001] The present invention is aimed at the fault diagnosis of the degraded state of the aero-engine. In order to solve the problem that the amount of fault data is small in a certain degraded state, the data collected in the non-degraded state is used to supplement, and based on the extreme learning machine, the data collected in the two fields are combined by transfer learning. Information is fully utilized. Background technique [0002] Fault diagnosis is an important part of aero-engine health management, and it is of great significance to ensure the healthy operation of aircraft and engines. Since 90% of aeroengine failures are caused by air circuit components, it is very necessary to perform fault diagnosis on air circuit components. Changes in flow and efficiency can directly reflect the health of engine components, but they cannot be directly observed. However, some measurable parameters on the engine, such as temperature, pressure, speed, etc., ca...

AI Technical Summary

Problems solved by technology

[0009] In order to solve the problem that a fault diagnosis model with good performance cannot be trained due to insufficient fault data when the aero-engine degrades to a certain stage, the present invention adopts the idea of ​​transfer learning, uses the data collected when it is not degraded as the source domain data, and utilizes The data collected under the current degradation state is used as the target domain data, and an ELM-based aero-engine fault diagnosis model is designed to improve the effectiveness of engine fault diagnosis

Images