Gear fault diagnosis method based on SVD decomposition and noise reduction and correlation EEMD entropy features

Abstract

The invention discloses a gear fault diagnosis method based on the SVD decomposition and noise reduction and correlation EEMD entropy features. The method includes utilizing an acceleration vibration sensor to acquire experimental platform gear vibration signals including four types of faults, namely gear normality, gear tooth breaking, gear tooth missing and gear wearing; performing noise reduction on the signals, of four gear states, containing simulated strong noise background of Gaussian white noise by the SVD decomposition method with correlation analysis and noise ratio optimization; decomposing the four types of noises by the EEMD method after noise reduction, and selecting valid IMF components according to correlative coefficients; performing sample entropy calculation on the valid IMF components, and establishing feature vectors composed of the IMF samples; identifying the four different types of gear faults through a PNN neural network. The method is effective and is capable of recognizing the gear fault types on the strong-noise background effectively.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis and relates to a gear fault diagnosis method based on SVD decomposition noise reduction and correlation EEMD entropy features. Background technique [0002] As an important part of rotating machinery, gear failure will reduce the working efficiency of the machine and even cause major economic losses. Therefore, the study of gear condition monitoring and fault diagnosis technology has important practical significance for improving the operation efficiency and maintenance efficiency of mechanical equipment and avoiding personnel and property losses. [0003] Gear fault diagnosis technology based on vibration signal analysis is an effective diagnosis method with high accuracy. Common diagnostic methods such as: time-frequency characteristic parameter method, cepstrum method, EMD decomposition, etc. However, in the process of signal processing, these methods have their own limitations for th...

AI Technical Summary

Problems solved by technology

However, in the process of signal processing, these methods have their own limitations for the nonlinear and non-stationary signals generated by gear transmission.

The different indicators in the time-frequency characteristic parameter method are only effective for the identification of specific gear defects; for complex conditions such as strong noise backgrounds, it is difficult to find the defect frequency of gears with the cepstrum method; the traditional Empirical Mode Decomposition (EMD) method It was proposed by N.E.Huang in 1998. Because it is suitable for the study of nonlinear and non-stationary signals, it has been widely used in recent years. However, there are still many problems in the EMD method, including endpoint effects, modal mixing, and many iteration cycles.

Images