Wind power rotary support surface defect detection method

Abstract

The invention provides a wind power rotary support surface defect detection method. According to the method, a low-angle 15-degree irradiation direction is utilized to show a texture direction. For ambient light interference, a low-angle strip-shaped light source can effectively relieve the ambient light interference. The detection algorithm combines a digital image processing method with SVM machine learning. The beneficial effects of the method are as follows: because an input workpiece image is simple in content and relatively single in color or gray level distribution, the algorithm can beused for avoiding the interference of adverse factors that the algorithm is very sensitive to noise and target size and cannot effectively cope with the condition that the image content is relativelycomplex, and has the characteristics of being simple in operation, high in speed and capable of realizing real-time processing. Besides, in some environments, if a vectorization form is used, operation circulation can be performed more quickly, and a multi-thread parallel processing method can also be easily adopted. The algorithm provided by the invention is small in calculation amount, high inefficiency and relatively high in accuracy.

Description

technical field [0001] The invention relates to the fields of digital image processing technology and machine vision technology, and in particular to collecting specific texture images on the surface of a wind power slewing support, and performing defect detection by image processing or feature extraction combined with machine learning for different types of textures. Background technique [0002] Wind power slewing support is one of the main products of wind power generation equipment, and its product quality must meet certain performance requirements, otherwise it will seriously affect the service life of the wind turbine. With the proposal of "Made in China 2025", green energy will be the country's primary energy choice, and wind energy, as one of the green energies, will greatly affect the use of future energy. Wind power generation has its own unique characteristics: due to long-term field work, harsh environment, and poor maintenance conditions, it is required that the...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method for detecting surface defects of wind power slewing supports, which solves the problems in the prior art that the surface defects of wind power slewing supports rely on manual observation, low efficiency, and high false detection rate; and the existing correct rate The high computational complexity of the alg...

Images