A Feature Extraction Method for Early Damage State of Rolling Bearings

Abstract

The invention discloses a feature extraction method for the early damage state of a rolling bearing. Firstly, the bias amount of the early damage signal of the rolling bearing is removed, and the variational mode decomposition method is used to perform adaptive decomposition processing on the vibration signal of the early damage state of the rolling bearing without bias. The eigenmode components are obtained, and then two time-domain characteristics of vibration energy and vibration kurtosis are calculated for each eigenmode component, and the initial characteristic data set of the early damage state of the rolling bearing is constructed using the time-domain characteristics, and then through the principal component analysis method The feature dimensionality reduction is performed on the initial feature set, and then a low-dimensional and efficient feature vector is obtained, which realizes the effective extraction of the feature information of the early damage state of the rolling bearing. The algorithm and program of the feature extraction method of the early damage state of the rolling bearing provided by the present invention are easy to implement, the whole process does not require manual participation, the degree of automation and intelligence is high, the cost is low, the accuracy is high, and it is easy to operate and implement, which is the safe operation of the bearing and equipment. Provides a reliable basis for judgment.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis and signal processing and analysis, and in particular relates to a feature extraction method for the early damage state of a rolling bearing. Background technique [0002] Rolling bearings are widely used in mechanical equipment in many fields such as electric power, metallurgy, petrochemical, transportation, etc. due to their advantages of high running accuracy, small friction coefficient, easy lubrication, easy assembly and mass production. Rolling bearings play a very important role in the stability, safety and reliability of mechanical equipment. Therefore, monitoring and diagnosing its damage state, especially the early damage state, can effectively reduce the probability of equipment failure, which will improve the production efficiency of enterprises and ensure Production safety is of great significance. At present, the monitoring and diagnosis of the damage state of rolling bearin...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the deficiencies pointed out in the above-mentioned background technology, the present invention provides a feature extraction method for the early damage state of rolling bearings, which aims to solve the problem that the existing rolling bearing damage diagnosis methods in the above-mentioned background technology cannot effectively extract the feature information in the early damage vibration signal of the bearing , it is difficult to timely diagnose the early damage state of the bearing

Images