A Rolling Bearing Fault Detection Method Based on Graph Similarity Feature Extraction

Abstract

The invention discloses a rolling bearing fault detection method based on graph similarity feature extraction. From the angle of graph similarity feature extraction, hidden features in non-stationary rolling bearing vibration signals are excavated, and the rolling bearing fault detection is carried out on this basis. Specifically, the method of the present invention first transforms the vibration signal into a graph matrix that can reflect the similarity between the signals according to the interval, and then uses the graph feature extraction algorithm to perform feature extraction on the graph matrix. Finally, the extracted features are used to judge whether the rolling bearing is faulty or not. The advantage of the method of the present invention is that the vibration signal can be converted into a graph matrix that can reflect the distance similarity between the vibration signals, and the feature extraction is performed on the graph matrix, and the feature analysis and extraction of the vibration signal of the rolling bearing are realized from the perspective of the time domain. And it does not involve complex calculations, and the implementation is simple.

Description

technical field [0001] The invention relates to a bearing fault detection method, in particular to a rolling bearing fault detection method based on graph similarity feature extraction. Background technique [0002] With the development of industrial technology towards intelligence, technology and integration, the functional requirements and operating conditions of modern mechanical equipment have gradually improved, and higher requirements have been placed on the reliability of equipment. The research on rolling bearing maintenance technology has gradually gained attention. Rolling bearings are widely used in rotating machinery and equipment as a key functional component that supports rotating bodies and reduces friction coefficient. The quality of their working performance is directly related to the normal operation of the equipment. Bearings are inevitably subjected to axial loads and cyclic alternating loads during operation, and are prone to failure forms such as fatigu...

AI Technical Summary

Problems solved by technology

The development of signal analysis based on Fourier transform is slow, mainly due to its large amount of calculation

Images