Method, apparatus and system for diagnosing bearing faults

Abstract

The embodiments of the invention disclose a method for diagnosing bear faults. The method includes the following steps: pre-processing a vibration signal of a bearing before using the local mean decomposition method to decompose the vibration signal, i.e., using the median filtering method to filter the background noise in the vibration signal, then extracting feature information from the signal which is pre-processed, and conducting fault diagnosis on the bearing based on fault feature information. According to the application, the technical solution uses the median filtering method to filter the background noise in an original signal, effectively increases the accuracy in extracting the fault feature information, is conducive to the increase of detection accuracy of bearing faults, and is conducive to normal and healthy operation of an entire device. In addition, the embodiments of the invention also provide a corresponding apparatus and system, which makes the method more practical. The apparatus and the system have corresponding advantages.

Description

Technical field [0001] The invention relates to the field of mechanical fault diagnosis, in particular to a bearing fault diagnosis method, device and system. Background technique [0002] With the development of the machinery manufacturing industry, bearings as a key component of mechanical equipment have also been greatly developed. Bearing is a pivotal component in contemporary mechanical equipment. Its main function is to support the mechanical rotating body, and to fix and reduce the friction coefficient of the load during the mechanical rotation. It can also be said that when other parts move relative to each other on the shaft, they are used to reduce the coefficient of friction in the process of power transmission and keep the shaft center position fixed. [0003] Among mechanical products, bearings are high-precision products. As an important basic component of various mechanical equipment, its accuracy, performance, life and reliability play a decisive role in the accura...

AI Technical Summary

Problems solved by technology

However, this method may extract fault feature information that does not meet the preset conditions when extracting fault feature information, which will cause the LMD algorithm to fail to converge, and thus cannot make a correct judgment on the working state of the bearing.

Images