Fan blade fault detection method based on sparse Bayesian learning and power spectrum separation
A sparse Bayesian, fan blade technology, applied in specific mathematical models, testing of mechanical components, testing of machine/structural components, etc., can solve problems such as high labor consumption and high requirements for inspectors, saving costs , The characteristics are clear and separable, avoiding the effect of excessive professional requirements
Active Publication Date: 2022-06-24
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
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
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] The invention provides a wind turbine blade fault detection method based on the separation of SBL algorithm and power spectrum. The microphone array is used to collect the acoustic signal of the wind turbine blade, the SBL algorithm is used for signal estimation, and the beam forming method is used for signal enhancement. Enhance the calculation of the normalized power spectrum of the signal to realize the fault detection of the fan blade.
[0048] In order to make the above objects, features and advantages of the present invention easier to understand, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.
[0049] like figure 1 As shown, the present invention provides a wind turbine blade fault detection method based on SBL algorithm and power spectrum separation, the method includes the following steps:
[0050] Step 1: Use the microphone array to collect three continuous sound signals of...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fan blade fault detection method based on sparse Bayesian learning and power spectrum separation. In this method, the microphone array is used to collect the acoustic signals radiated by three continuous and equal-length fan blades, and the sparse Bayesian learning algorithm is used to estimate the source signals of the three acoustic signals respectively, and the DOA estimation is performed on the estimated signals. Signal enhancement, calculate the power spectrum of the enhanced signal, and normalize the power spectrum. According to whether the normalized power spectrum of the three-segment acoustic signal is separated, it is judged whether there is a fault in the blade of the wind turbine. The fan blade fault detection method based on sparse Bayesian learning and power spectrum separation provided by the invention can largely remove the noise in the collected signal and accurately judge the fault of the wind generator blade.
Description
technical field [0001] The invention belongs to the field of spatial signal processing, and in particular relates to a wind turbine blade fault detection method based on sparse Bayesian learning (SBL algorithm) and power spectrum separation. Background technique [0002] As more and more attention is paid to renewable resources, 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 harsh environments such as mountain peaks or coasts, extreme humidity factors and changeable weather and environmental factors make wind turbines extremely prone to damage. The blades of wind turbines are more prone to failure because they are directly exposed to the outdoors. With the continuous expansion of energy demand, the size of the fan proportional to the average cost of energy, such as the tower height and blade size, is also increasing, which greatly increases the p...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N7/00G06K9/00G01N29/04G01M13/00
CPCG01N29/04G01M13/00G01N2291/106G06N7/01G06F2218/04G06F2218/08G06F18/29
Inventor 潘翔许蓉邱俭军
Owner ZHEJIANG UNIV