Rolling bearing condition monitoring method based on weighted similarity measure

Abstract

The invention discloses a rolling bearing state monitoring method based on weighted similarity measure. First, a vibration signal of a rolling bearing is converted into a binary symbol sequence according to the fluctuation trend of adjacent sequence points; then, the binary symbol sequence is converted into a word frequency sequence; and finally, the weighted similarity measure between a word frequency sequence corresponding to the initial state and each of word frequency sequences corresponding to other states is calculated, and the running state of the rolling bearing is monitored by taking the measure as a characteristic parameter. In the running process of the rolling bearing, if the change in the value corresponding to the weighted similarity measure at one moment relative to the value corresponding to the weighted similarity measure at a previous moment is over 20%, that the running state of the rolling bearing changes obviously at the moment can be judged, and the moment is taken as a moment when failure occurs. The method of the invention is suitable for processing complex rolling bearing vibration signals. By adopting the method, early failure of a rolling bearing can be detected timely and accurately. The method has good noise resistance and robustness, and is convenient for engineering application.

Description

technical field [0001] The invention relates to a bearing, in particular to a rolling bearing state monitoring method, which belongs to the field of rotating machinery state monitoring and fault diagnosis. Background technique [0002] Rolling bearings are the most commonly used rotating parts, and their fault features are usually weak, especially when the rolling bearing fault is in the early stage, its fault features are very difficult to extract. Therefore, early fault detection of rolling bearings is a difficult problem. [0003] At present, the traditional rolling bearing state monitoring methods include manual monitoring method, effective value method and kurtosis method. The above methods are all directly monitoring and analyzing the original signal. The noise and robustness are poor, and it is difficult to detect the early faults of rolling bearings in time and accurately. Contents of the invention [0004] The problem to be solved in the present invention is to ...

AI Technical Summary

Problems solved by technology

[0003] At present, traditional rolling bearing state monitoring methods include artificial monitoring method, effective value method and kurtosis method. The above methods are all directly monitoring and analyzing the original signal. The noise and robustness are poor, and it is difficult to detect the early faults of rolling bearings in time and accurately

Images