Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set

Abstract

The invention discloses a turboprop engine rotor system fault diagnosis method through combination of EEMD and a neighborhood rough set. The method comprises the steps of performing EEMD decomposition of an original signal of a turboprop engine rotor system in different fault states for obtaining a plurality of IMF components; extracting the original vibration signal and a plurality of different characteristic indexes contained in an IMF main component in the plurality of IMF components, and constructing an original combined characteristic set; evaluating the attribute importance of each characteristic in the original characteristic set according to a neighborhood rough set attribute reduction method, and selecting a characteristic set which is relatively sensitive to rotor system fault classification in the original characteristic set; inputting the sensitive characteristic set of a training sample into a support vector machine multi-classifier, determining an optimal combination of classifier parameters c and g in an index range, and performing classification and identification on the testing sample according to a trained SVM model. According to the turboprop engine rotor system fault diagnosis method, information which is hidden in the vibration signal and reflects a rotor system operation state can be mined in multiple aspects, thereby reducing fault characteristic redundancy and calculation complexity of the classifier.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of aero-engines, and in particular relates to a fault diagnosis method for a turboprop engine rotor system combining EEMD and neighborhood rough sets. Background technique [0002] The rotor system is an important part of an aero-engine, and its working state directly determines the reliability and safety of the complete engine. However, due to the long-term operation of the rotor system in the harsh environment of high temperature, high pressure and high speed, various failures often occur, which seriously affect its service life and the flight safety of the aircraft. At the same time, since the rotor is located inside the engine, there is little opportunity to disassemble the engine to detect whether the rotor structure has signs of failure such as fatigue cracking and wear when the whole machine is running without failure. Therefore, an effective and accurate fault diagnosis method is ...

AI Technical Summary

Problems solved by technology

However, due to the long-term operation of the rotor system in the harsh environment of high temperature, high pressure and high speed, various failures often occur, which seriously affect its service life and the flight safety of the aircraft.

Images