A rolling bearing fault identification method and system based on multi-dimensional entropy space distance

Abstract

This application discloses a rolling bearing fault identification method and system based on multi-dimensional entropy space distance, which collects the original vibration signals of rolling bearing normal working conditions and different fault types, and selects 10 sets of sample data for each working condition; uses EMD to analyze the sample data Perform noise reduction processing to obtain multiple IMF components; select the first 5 IMF components of each working condition, calculate the information entropy, energy entropy and permutation entropy of each group of sample data IMF component transformations for each working condition, and calculate the average value respectively ;Construct a three-dimensional space, randomly select a preset number of test data, calculate three kinds of entropy values ​​after transformation, and then calculate the spatial distance with the entropy value points of each working condition in the three-dimensional space in the previous step, and judge the test data and each kind of entropy value The distance between the types of bearing conditions ultimately determines the condition of the rolling bearing. Therefore, the fault features of the rolling bearing can be effectively extracted, thereby improving the accuracy of fault identification.

Description

technical field [0001] The present application relates to the technical field of fault diagnosis of rolling bearings, in particular to a rolling bearing fault identification method and system based on multi-dimensional entropy space distance. Background technique [0002] Rolling bearings are one of the most important components in rotating equipment at present. Once they are damaged, they will directly affect the safety performance of industrial equipment. Therefore, how to use the collected vibration signals of rolling bearings to effectively extract and diagnose rolling bearing faults The characteristic quantity of the type is of great significance to the detection and fault diagnosis of rolling bearings. [0003] At present, time-frequency analysis methods are generally used for fault diagnosis of rolling bearings at home and abroad, such as wavelet transform, Fourier decomposition, etc., but these methods have certain limitations. For example, wavelet transform needs t...

AI Technical Summary

Problems solved by technology

In the existing fault diagnosis technology, there are still problems such as the extracted feature quantity is not accurate enough, and the recognition rate is low.

Images