Entropy-Based Multi-source Wind Turbine Bearing Fault Diagnosis Method

Abstract

The invention discloses an entropy-based multi-source wind turbine bearing fault diagnosis method, comprising the following steps: (1) collecting data of a wind turbine bearing vibration signal by using acceleration sensors, performing EMD processing, windowed Welch method power spectrum analysis and power spectrum entropy calculation, and obtaining a feature physical quantity of the sample data;(2) adding an information entropy as the weight based on a bearing fault feature matrix to calculate a gray correlation degree of the sample data to be tested, and obtaining a BPA value as a BPA evidence; and (3) correcting the BPA evidence group based on a fuzzy interactive entropy, and merging the corrected evidence group to obtain a bearing fault diagnosis result. The entropy-based wind turbinebearing fault diagnosis method proposed by the invention can deal with partial data failure or abnormality caused by sensor damage in a plurality of bearing acceleration sensors.

Description

technical field The invention relates to the field of bearing fault diagnosis, in particular to a method for identifying bearing fault states based on multiple sensor information. Background technique With the progress and development of the times, electric energy plays an increasingly important role in national life and industrial production. Wind power generation is widely popular due to its technological advantages and large-scale existence of wind energy resources. Due to the increasingly complex and large-scale wind turbines, the probability of failure of the wind turbines is greatly increased. As a large-scale rotating machine, the wind turbine is a large-scale rotating machine, and the bearing plays the role of transmitting torque. The operating state of the bearing directly determines whether the equipment can work normally, and the bearing is usually in an extreme working environment and is prone to failure. Therefore, the bearing Fault diagnosis is particularly im...

AI Technical Summary

Problems solved by technology

The technical problem to be solved by the present invention is: the traditional Fourier analysis cannot be used directly to obtain the power spectrum entropy for the non-stationary and nonlinear wind turbine bearing fault vibration signal; when the BPA is obtained based on the gray correlation analysis, the effect of the equal weight gray correlation coefficient is used. Not obvious enough; a single sensor can identify high-risk and uncertain bearing faults, and a multi-source wind turbine bearing fault diagnosis method based on entropy is proposed

Images