Rolling bearing fault diagnosis method based on deconvolution and envelope spectrum

Abstract

The invention discloses a rolling bearing fault diagnosis method based on deconvolution and an envelope spectrum. In order to study influence on classification and identification results of rolling bearing working states under different damage degrees, rolling bearing rolling body fault signals are analyzed, the rotating speed of a rotating shaft is 1800r / min, the sampling frequency is 12000Hz, and the damage degrees are divided into a mild degree, a moderate degree and a severe degree according to diameters of damage points. According to the rolling bearing fault diagnosis method based on thedeconvolution and the envelope spectrum, the structure is scientific and reasonable, and the usage is safe and convenient. The rolling bearing fault diagnosis method based on the deconvolution and the envelope spectrum comprises the steps that firstly, a fault feature of a rolling bearing vibration signal is enhanced by using MCKD algorithm; the enhanced signal is carried out VMD decomposing; IMFcomponents containing main fault feature information are selected based on energy entropy increment and a kurtosis criterion; an envelope spectrum feature amplitude ratio and envelope spectrum entropy of each sensitive IMF component are extracted to better reflect and quantify the fault feature information; and a fault state is identified by using fuzzy C-means clustering algorithm to realize thediagnosis of a working state and a fault type of a rolling bearing.

Description

technical field [0001] The invention relates to the field of rolling bearing fault diagnosis, in particular to a rolling bearing fault diagnosis method based on deconvolution and envelope spectrum. Background technique [0002] Rolling bearing is the most commonly used part in mechanical equipment. It provides reliable support for the mechanical structure. Its operating status will directly affect the operating safety and related performance of the equipment. Due to the harsh working environment, rolling bearings are prone to wear and scratches in the early stages of the working cycle. However, the operating conditions of mechanical equipment are complex, and the generated vibration signals are often mixed with strong external noise, which leads to the submergence of fault characteristic information, which is difficult to identify and extract. Effective extraction of weak fault features reflecting rolling bearings has become a hot and difficult point in the field of fault di...

AI Technical Summary

Problems solved by technology

[0002] Rolling bearing is the most commonly used part in mechanical equipment. It provides reliable support for the mechanical structure. Its operating status will directly affect the operating safety and related performance of the equipment. Due to the harsh working environment, rolling bearings are prone to wear and scratches in the early stages of the working cycle. However, the operating conditions of mechanical equipment are complex, and the generated vibration signals are often mixed with strong external noise, which leads to the submergence of fault characteristic information, which is difficult to identify and extract. Effective extraction of weak fault features reflecting rolling bearings has become a hot and difficult point in the field of fault diagnosis;

Images