Intelligent Rolling Bearing Fault Identification Method Based on Residual Signal Characteristics of Empirical Mode Decomposition

Abstract

The invention discloses an intelligent recognition method for rolling bearing faults based on empirical mode decomposition residual signal characteristics. The method is to perform intelligent identification on rolling bearing fault patterns by combining the energy characteristics of empirical mode decomposition residual signals and the time domain characteristics of vibration signals and using anetwork model that optimizes the parameters of a support vector machine by a genetic algorithm. The invention combines the energy characteristics of the empirical mode decomposition residual signal and the time domain characteristics of the vibration signal and uses a network model that optimizes the parameters of a support vector machine by a genetic algorithm in order to be used for bearing fault diagnosis. The experimental results show that on the basis of the small sample situation, the type of rolling bearing faults can be more accurately identified, thus helping the pattern recognition and intelligent diagnosis of rolling bearing faults.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method, more specifically, it is an intelligent rolling bearing fault identification method based on the residual signal characteristics of empirical mode decomposition. Background technique [0002] The parts and components in rotating machinery are complex and compact in structure. Rolling bearings are widely used as one of the positioning and supporting components. They are a common but critical type of mechanical components in equipment. The working characteristics of rotating mechanical equipment are: the rotor runs at high speed and the operating environment is harsh. In addition, the structure of the rotor itself is relatively complex, which is prone to damage, causing failure or even failure, resulting in mechanical equipment failure or unplanned shutdown. Relevant studies also show that among the common faults of rotating machinery, faults related to rolling bearings account for nearly...

AI Technical Summary

Problems solved by technology

[0004] However, the experimental process of the above method is very complicated and the pertinence is not strong.

Images