Rolling bearing fault diagnosis method and system based on high-order origin moment

Abstract

The application discloses a rolling bearing fault diagnosis method and system based on a high-order origin moment. The rolling bearing fault diagnosis method based on the high-order origin moment comprises the following steps of: extracting sample data of a normal operating condition and a fault operating condition during the operation of a rolling bearing, and performing standardization processing on the data; using a wavelet decomposition method to divide a time domain signal into five layers of signals; calculating a fourth-order origin moment of the normal operating condition and three fault operating conditions; taking the angle degree of the vector angle as the feature, combining the calculated fourth-order origin moment of the five layers of signals into two vectors, which are vector A and vector B separately, and calculating the angle between the vector A and the vector B; determining distinguishing ranges of the four operating conditions, and calculating the correct rate of different data sizes; establishing an index function of a relationship between the correct rate and the data size, and selecting the optimal data size; and establishing an SVM support vector machine classifier, and inputting training samples and test samples into the SVM classifier for classification and diagnosis. Therefore, the features of the rolling bearing faults can be effectively extracted, and the recognition of the rolling bearing faults is improved.

Description

technical field [0001] The present application relates to the technical field of fault diagnosis of rolling bearings, in particular to a method and system for fault diagnosis of rolling bearings based on high-order origin moments. Background technique [0002] The dispersion of rolling bearing life is greater than that of other rotating mechanical components. Due to the above-mentioned characteristics of rolling bearings, some rolling bearings have various failures before reaching their designed service life. Therefore, the operation data of rolling bearings is collected, and the working status and faults of rolling bearings are diagnosed and predicted in real time based on the collected data, so as to judge whether the equipment can run safely, reliably and smoothly, and timely maintenance and treatment of faulty bearings can be effectively Avoid the impact. Therefore, it is very necessary for us to collect and analyze the original vibration signals of rolling bearing faul...

AI Technical Summary

Problems solved by technology

The nonlinear, non-stationary and other complex conditions of the signal attributes collected for rolling bearing faults make the recognition of faults low

Images