Bearing fault diagnosis method based on improved generalized S transformation

Abstract

The invention relates to a bearing fault diagnosis method based on improved generalized S transformation, and the method comprises the following steps: installing an acceleration sensor on a rotating mechanical device, and measuring the vibration through the acceleration sensor, thereby obtaining a vibration signal; according to the model of the bearing, an original adjusting parameter k is set to be 1, the vibration signals are input into set generalized S transformation S (t, f, k) to be analyzed, t is a time sequence, f is sampling frequency and the like; the method comprises the following steps: setting initial generalized S transformation and calculating to obtain the standard crowding degree of various fault types of the bearing; the method comprises the following steps: collecting vibration data of the same bearing, calculating the congestion degree of a signal, carrying out corresponding parameter adjustment through judgment of the congestion degree, determining an optimal adjustment parameter through comparison of global optimal resolution, carrying out improved generalized S transformation analysis, and finally completing fault diagnosis according to an analysis effect so as to realize accurate fault diagnosis.

Description

technical field [0001] The invention relates to the field of bearing detection, in particular to a bearing fault diagnosis method based on an improved generalized S transform. Background technique [0002] Rotating machinery units are complex in structure and work under complex alternating loads for a long time, and unit failures occur from time to time. Among them, bearings are one of the components with the highest failure rate in rotating machinery, and the condition monitoring and fault diagnosis of bearings are imminent. If the fault is not detected in time, it is easy to cause damage to the rotating machinery and seriously affect the economic benefits. Therefore, the fault diagnosis of rotating machinery bearings is of great significance. [0003] During the transmission process, the bearing is subjected to bending load, vibration load, etc., so it is very prone to failure. The fault diagnosis of the bearing is to extract the fault features from the vibration signal b...

AI Technical Summary

Problems solved by technology

The generalized S-transform is a commonly used time-frequency analysis method. It maintains the absolute phase information of the signal, and its time-frequency resolution changes with the frequency. The width of the window function can be adjusted according to the time-frequency characteristics of the analyzed signal to achieve the optimum Excellent time-frequency resolution, but in the actual operation process, adjusting the width of the window function often relies on human experience, and it is impossible to achieve adaptive transformation in combination with working conditions and other conditions, and the operation is complicated

Images