Bearing fault diagnosis method based on parameter optimization VMD and weighted Gini index

Abstract

The invention discloses a bearing fault diagnosis method based on parameter optimization VMD and a weighted Nick index; the method comprises the steps: collecting a full-life-cycle vibration signal of a bearing from a healthy state to a damaged state, and obtaining a vibration acceleration signal; initializing parameters of variational mode decomposition and a carnivorous plant optimization algorithm, and calculating a fitness function value; according to the fitness function value, optimizing a variational mode decomposition algorithm by adopting a carnivorous plant optimization algorithm to acquire a VMD parameter combination with the optimal vibration acceleration signal decomposition effect; and carrying out variational mode decomposition by using the VMD parameter combination with the optimal vibration acceleration signal decomposition effect, calculating an envelope kurtosis value, carrying out envelope demodulation analysis on a mode component with the maximum envelope kurtosis value, and then judging a bearing fault type. The method can accurately and efficiently extract weak features of the rolling bearing fault signal under strong and complex background noise, provides a theoretical method for avoiding major accidents, economic losses and the like caused by bearing faults, and has important reference value.

Description

Technical field [0001] The present invention belongs to the field of rocket engine fault diagnosis, involving a bearing fault diagnosis method based on parameter optimization VMD and weighting Kini index. Background technique [0002] The turbine pump is a key component of a liquid rocket engine that has long been operated at high temperatures, low temperatures, high pressure, low pressure and high speed conditions, and the thermodynamic environment is extremely complicated. The rolling bearings are the core components of the turbine pump, which is operated for a long time while withstanding various forms of stress extrusion, friction, and it is easy to fail. Once the rolling bearing fails, it will directly affect the security and stable operation of the rocket engine. Therefore, the fault diagnosis of rocket engine turbine pump bearings is therefore necessary, which is very important for ensuring the smooth launch of the rocket. [0003] Rocket engine turbine pump bearings use s...

AI Technical Summary

Problems solved by technology

(2) High energy

However, the defect of VMD is that the number of decompositions K and the secondary penalty factor α must be determined in advance, and this parameter has a significant impact on the decomposition accuracy

Parameters determined by manual experience, the decomposition accuracy is not high, and the diagnosis efficiency is low

[0005] In the prior art, the vibration signal of the turbo pump bearing has a wide frequency spectrum, large energy, strong mutation, and difficult fault feature extraction.

Images