Blade fault diagnosis method based on sound periodicity

Abstract

The invention provides a blade fault diagnosis method based on sound periodicity. The method comprises the following steps: extracting a feature vector matrix mfcc from collected sound signals of a blade by using an Mel Frequency Cepstrum Coefficant (MFCC) method, and defining a periodic frame category according to the periodicity of the sound signals of the blade; secondly, clustering all frame signals into two types by adopting a K _ means algorithm, and establishing a periodic frame type probability matrix according to a clustering result; and finally, determining the final category of eachframe of signal according to the probability matrix, and realizing fault diagnosis of the fan blade through a bar chart on a category number time domain. According to the method of the invention, non-contact online monitoring and diagnosis of the blade can be realized, the adopted sound signal is easy to obtain, and the method has potential engineering application values.

Description

technical field [0001] The invention relates to a blade fault diagnosis method based on sound periodicity. When using the unsupervised learning K_means algorithm for blade fault diagnosis, considering the characteristics of wind power generator blade sound periodicity, the accuracy of fault diagnosis can be improved. The invention belongs to Fault diagnosis technical field. Background technique [0002] Wind farm blades operate in the harsh open-air environment for a long time, and failures such as cracking, surface shedding, and abrasion often occur. These failures of the blades will not only affect the efficiency of the wind turbine to capture wind energy, but also reduce the service life of the blades and increase the cost of operation and maintenance. . [0003] At present, the fault diagnosis of blades based on sound signals has potential application value. The steps of fault diagnosis for blades in domestic and foreign researches are generally divided into two parts. ...

AI Technical Summary

Problems solved by technology

[0002] Wind farm blades operate in the harsh open-air environment for a long time, and failures such as cracking, surface shedding, and abrasion often occur. These failures of the blades will not only affect the efficiency of the wind turbine to capture wind energy, but also reduce the service life of the blades and increase the cost of operation and maintenance.

Images