A Method of Fault Diagnosis of Rolling Bearings Based on LCD‑MF

Abstract

The present invention is a rolling bearing fault diagnosis method based on LCD‑MF, using local characteristic scale decomposition to obtain several intrinsic scale components (ISC), and selecting useful intrinsic scale components to calculate Teager energy operator (TEO) respectively, so as to obtain each The instantaneous amplitude and instantaneous frequency corresponding to each intrinsic scale component. Then, the instantaneous amplitude of each intrinsic scale component is analyzed by multifractal detrended fluctuation analysis (MFDFA), and its generalized Hurst exponent is extracted as the multifractal feature of the intrinsic scale component. Afterwards, principal component analysis (PCA) is used for dimensionality reduction, and the results of principal component analysis are used as fault feature vectors. Through the real-time collection of the working vibration signal of the rolling bearing under variable working conditions, the collected vibration signal is processed through the above steps to obtain the corresponding fault feature vector M, and the fault feature vector is identified to realize the fault detection and fault location of the rolling bearing.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of rolling bearings, in particular to an LCD-MF-based fault diagnosis method for rolling bearings. Background technique [0002] The role of rolling bearings is to support the rotating shaft and the parts on the shaft, and maintain the normal working position and rotation accuracy of the shaft. It is characterized by convenient use and maintenance, reliable operation, good starting performance, and high bearing capacity at medium speeds. Rolling bearings are key components commonly used in mechanical equipment, and whether their working status is normal is directly related to the normal operation status of the entire production line. Faults of rolling bearings often lead to a significant reduction in productivity, and in severe cases, even huge property losses. In order to ensure that rolling bearings operate in good condition, it is necessary to carry out condition monitoring and fault d...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the defects of lack of sufficient robustness, lack of adaptability to changes in working conditions and poor classification effect on different fault degrees in commonly used rolling bearing fault diagnosis methods

Images