Fan blade fault detection method based on sparse Bayesian learning and power spectrum separation

Abstract

The invention discloses a fan blade fault detection method based on sparse Bayesian learning and power spectrum separation. According to the method, firstly, a microphone array is used for collecting three sections of sound signals radiated by the fan blade which are continuous and equal in length, a sparse Bayesian learning algorithm is used for estimating source signals of the three sections of sound signals respectively, DOA estimation is carried out on the estimated signals, signal enhancement is carried out through beam forming, a power spectrum of the enhanced signals is calculated, normalization is carried out on the power spectrum, and whether the blade of the wind driven generator has a fault or not is judged according to whether the normalized power spectrums of the three sections of sound signals are separated or not. According to the fan blade fault detection method based on sparse Bayesian learning and power spectrum separation provided by the invention, the noise in the acquired signal can be greatly removed, and the blade fault of the wind driven generator can be accurately judged.

Description

technical field [0001] The invention belongs to the field of spatial signal processing, and in particular relates to a wind power generator blade fault detection method based on sparse Bayesian learning (SBL algorithm) and power spectrum separation. Background technique [0002] As renewable resources are paid more and more attention, the importance of wind turbines, as an important component of wind power generation, has become increasingly prominent. Because wind turbines are often built in remote areas with relatively harsh environments such as mountains or coasts, extreme humidity factors and changeable weather and environmental factors, wind turbines are prone to damage. The blades of wind turbines are more prone to failure due to their direct exposure to the outdoors. With the continuous expansion of energy demand, the fan size proportional to the average cost of energy, such as tower height and blade size, is also increasing, which greatly increases the probability o...

AI Technical Summary

Problems solved by technology

This type of method has high requirements for inspectors, requires inspectors to have certain professionalism and experience, consumes a lot of manpower, and can only observe damage and faults on the surface of blades

Images