Rolling bearing fault diagnosis method under incomplete sample condition

Abstract

The invention discloses a rolling bearing fault diagnosis method under an incomplete sample condition. The method comprises the steps that firstly, collecting vibration acceleration signals of a rolling bearing through an acceleration sensor, conducting frequency domain feature extraction on vibration acceleration, selecting extracted frequency domain features, and constructing and an input feature vector of a fault diagnosis model; secondly, constructing a reference evidence matrix table and a joint reference evidence matrix table; determining the correlation between different reference evidences according to the joint evidence matrix table; fusing a plurality of reference evidence combinations activated by an input sample vector, further fusing fusion results by adopting an evidence reasoning rule to determine a parameter optimization model, and finally performing fault diagnosis on the rolling bearing based on an optimal parameter set. According to the method, correlation between evidences is fully considered, sample fault features are effectively recognized, and effective diagnosis of the typical fault mode of the rolling bearing under the condition that missing values exist insample data can be well achieved.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method under incomplete sample conditions, and belongs to the technical field of state monitoring and fault diagnosis of rotating mechanical equipment. Background technique [0002] Rolling bearings are a kind of precision mechanical components that reduce friction loss. Due to the influence of manufacturing, installation and operating environment, they are prone to damage in the electromechanical system, which directly affects the working status of rotating machinery, and then affects the reliability of the entire electromechanical system. According to statistics, among the faults of rotating machinery, about 30% of the mechanical faults are caused by the damage of rolling bearings. Therefore, it is of great significance to study the fault diagnosis of rolling bearings to ensure the normal and reliable operation of electromechanical equipment. [0003] At present, the fault diagnosis methods ...

AI Technical Summary

Problems solved by technology

The application of the time-frequency domain analysis method makes up for the defect that the traditional method is only suitable for stationary signal analysis, but it does not consider the lack of sample data

However, in the actual monitoring process, due to the limitations of sensors, human or technical factors, the phenomenon of missing fault feature data often occurs, resulting in incomplete fault diagnosis samples.

Establishing a rolling bearing fault diagnosis model based on incomplete samples makes the model lose a lot of useful data information, further increases the uncertainty of diagnostic information, and reduces the effectiveness of fault diagnosis

Images